© 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. 15492
    Prev
    Next
    INDEX
    Explanations

    conditional circumstances and possibilities

    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
    or
    -3.00
    o
    -2.97
    e
    -2.86
     当
    -2.78
     votre
    -2.67
    other
    -2.55
    er
    -2.53
    ../../
    -2.52
    aş
    -2.50
    u
    -2.50
    POSITIVE LOGITS
    ↵
    3.48
    .
    2.91
    髏
    2.86
    趼
    2.84
    辚
    2.69
    が存在
    2.53
    尛
    2.53
     ſtate
    2.53
     メニュー
    2.45
    ftrag
    2.41
    Activations Density 0.004%

    No Known Activations