© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63687
    Prev
    Next
    INDEX
    Explanations

    InnoDB ENGINE and collation

    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_34/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
     вкусу
    -0.87
    etary
    -0.81
    anda
    -0.81
     tł
    -0.77
    弉
    -0.75
    Ralph
    -0.74
     scala
    -0.74
    Haz
    -0.72
     кры
    -0.71
     roster
    -0.71
    POSITIVE LOGITS
     Inno
    1.12
     collation
    1.10
     coll
    1.03
    collation
    0.97
     Coll
    0.97
    Coll
    0.96
    collate
    0.96
    Inno
    0.93
    ENGINE
    0.92
    COLL
    0.92
    Activations Density 0.148%

    No Known Activations