© 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. 63843
    Prev
    Next
    INDEX
    Explanations

    the quantity

    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
    МЕН
    -0.88
    人在
    -0.80
     الدولة
    -0.79
    americano
    -0.75
     version
    -0.73
    rightarrow
    -0.73
     füh
    -0.73
    ित
    -0.72
    委员
    -0.71
     heißen
    -0.70
    POSITIVE LOGITS
     lot
    4.78
     bunch
    3.44
    Lot
    3.13
    lot
    2.86
     Lot
    2.81
    bunch
    2.47
     LOT
    2.22
    LOT
    2.08
     lots
    2.05
    Bunch
    1.97
    Activations Density 0.027%

    No Known Activations