© 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. 22-GEMMASCOPE-RES-131K
    7. 25221
    Prev
    Next
    INDEX
    Explanations

    relative comparisons

    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_22/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
    ropical
    -2.39
    ayage
    -2.31
     autén
    -2.08
    称号
    -2.05
    ৣ
    -1.97
     reconocida
    -1.97
    萇
    -1.97
     éstos
    -1.95
     â
    -1.92
     éstas
    -1.92
    POSITIVE LOGITS
     That
    2.88
     所以
    2.48
    あっという
    2.44
    0
    2.33
    ?’
    2.27
     而
    2.23
    ”،
    2.22
    ⢓
    2.20
    ･･
    2.19
    ，，
    2.17
    Activations Density 0.016%

    No Known Activations