© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2214
    Prev
    Next
    INDEX
    Explanations

    ethically

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires on numeric tokens that are floating‐point numbers (i.e. tokens containing a decimal point).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    the word "as" when it appears in formal or academic contexts, particularly in biographical descriptions, religious texts, and technical documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    short function words, especially common prepositions that link phrases within sentences.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tend
    0.90
     Elkus
    0.87
    eem
    0.86
     hugely
    0.84
    eer
    0.81
    ../../../
    0.81
    twin
    0.80
    tie
    0.80
    tuvo
    0.80
    neuron
    0.79
    POSITIVE LOGITS
    ث
    0.79
     mưa
    0.71
    ق
    0.70
    簀
    0.70
    菟
    0.66
    Dimethyl
    0.64
    
    0.63
    æ
    0.63
     températures
    0.63
    Certified
    0.63
    Activations Density 0.000%

    No Known Activations