© 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. 72315
    Prev
    Next
    INDEX
    Explanations

    shift

    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
    却不
    -2.88
    鹟
    -2.44
    许久
    -2.42
    說
    -2.42
    ències
    -2.42
    sandalia
    -2.39
    鸕
    -2.39
    ჻
    -2.38
     “(
    -2.28
    お世話
    -2.28
    POSITIVE LOGITS
    ╿
    2.80
    籥
    2.72
     奶
    2.70
     If
    2.66
    </h5>
    2.66
    ?
    2.61
    汌
    2.55
    のみ
    2.48
    ),
    2.47
     &
    2.45
    Activations Density 0.009%

    No Known Activations