© 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. 4070
    Prev
    Next
    INDEX
    Explanations

    question/answer structure

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

    The neuron lights up on content-bearing lexical words (important nouns and verbs) rather than on function words.

    oai_token-act-pair · o4-miniTriggered 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
     außer
    0.81
     použív
    0.81
    擡
    0.80
    jsko
    0.79
    添加到
    0.79
     bietet
    0.78
    ITEMS
    0.77
    वासियों
    0.76
    ISATION
    0.76
    INFO
    0.75
    POSITIVE LOGITS
     uterine
    0.85
               
    0.73
     subcutaneous
    0.71
     Фі
    0.70
    d
    0.70
                
    0.69
    separable
    0.65
     فائ
    0.65
     CF
    0.64
    degenerate
    0.64
    Activations Density 0.000%

    No Known Activations