© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 10680
    Prev
    Next
    INDEX
    Explanations

    separating clauses or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    தான்
    0.93
     кілька
    0.83
    <unused2213>
    0.83
    чә
    0.81
    itinéraire
    0.81
    рил
    0.80
    imètre
    0.80
    âmica
    0.79
    ículos
    0.79
    ϫ
    0.78
    POSITIVE LOGITS
     Whilst
    1.90
     therefor
    1.77
     والتي
    1.77
     whilst
    1.69
     אשר
    1.65
     또한
    1.63
     ,
    1.61
     والذي
    1.59
    또한
    1.58
    ,(
    1.56
    Activations Density 0.014%

    No Known Activations