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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14356
    Prev
    Next
    INDEX
    Explanations

    breakdown of information how

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

    The neuron fires strongly on relatively rare or information-rich tokens (i.e. high-TF-IDF or unusual 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
    inan
    0.77
    इल
    0.73
    >>>
    0.71
    株
    0.71
     utilizes
    0.70
    它的
    0.68
    是很
    0.67
    iesz
    0.67
    是用
    0.67
    I
    0.66
    POSITIVE LOGITS
     botão
    0.81
     Wrong
    0.77
     Surprisingly
    0.76
     Remarkably
    0.76
    챌
    0.76
     doigt
    0.75
     와
    0.75
     잘못
    0.74
     Largest
    0.74
    ம்
    0.73
    Activations Density 0.000%

    No Known Activations