© 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. 221
    Prev
    Next
    INDEX
    Explanations

    programming code examples

    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
    <unused1162>
    0.66
    ༸
    0.65
    Discrimin
    0.65
    <unused1071>
    0.64
     prothorace
    0.63
     `:`
    0.63
    ፫
    0.63
    <unused1828>
    0.62
    <unused417>
    0.61
     TNumber
    0.60
    POSITIVE LOGITS
    0.69
    č
    0.62
     pequena
    0.61
     be
    0.58
     muito
    0.58
     organização
    0.58
     fortes
    0.57
    أ
    0.57
    Г
    0.56
     world
    0.55
    Activations Density 0.000%

    No Known Activations