© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113935
    Prev
    Next
    INDEX
    Explanations

    reclining chairs, cleft lip, recessive mutations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -3.55
     For
    -3.53
    ↵↵
    -3.42
    *
    -3.36
     If
    -3.33
    <b>
    -3.31
    {
    -3.23
    $
    -3.09
    &
    -3.02
                
    -2.98
    POSITIVE LOGITS
    ꜆
    3.44
     $\&$
    3.06
     aussit
    2.98
    ⑊
    2.95
    ギュア
    2.89
    mpagne
    2.81
     sprüche
    2.78
    และ
    2.75
    ㆆ
    2.73
    絝
    2.72
    Activations Density 0.006%

    No Known Activations