© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9438
    Prev
    Next
    INDEX
    Explanations

    definition or classification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     πολι
    0.56
    COMP
    0.55
    willing
    0.54
    cock
    0.53
    polymer
    0.53
    Cock
    0.53
    コン
    0.52
    kmeans
    0.52
    練
    0.52
    ub
    0.52
    POSITIVE LOGITS
     хуже
    0.59
    [/
    0.55
     decipher
    0.52
     DecodingError
    0.52
     fresh
    0.52
     Oss
    0.52
     distinguish
    0.51
     ros
    0.51
     [/
    0.51
     identifications
    0.51
    Activations Density 0.039%

    No Known Activations