© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5044
    Prev
    Next
    INDEX
    Explanations

    percentages and ratios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     অন্ত
    0.53
     still
    0.52
    ృష్
    0.51
    @-
    0.50
     টি
    0.50
    cess
    0.48
     marched
    0.48
    够
    0.48
    勬
    0.48
     Downs
    0.48
    POSITIVE LOGITS
     تريد
    0.63
     publicar
    0.59
     hebre
    0.59
    菓
    0.57
    publik
    0.56
     पूजा
    0.55
     Hebre
    0.55
    果た
    0.55
    прав
    0.55
    袷
    0.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.