© 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. 10-GEMMASCOPE-RES-131K
    7. 67962
    Prev
    Next
    INDEX
    Explanations

    world-class and renowned entities

    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
    decoración
    -2.22
    𖤣
    -2.16
     sám
    -2.11
    𓇼
    -2.09
     pretože
    -2.08
    慊
    -2.05
    騭
    -2.03
     rám
    -1.97
    ፨
    -1.96
    🡺
    -1.95
    POSITIVE LOGITS
    f
    2.48
    If
    2.25
    However
    2.23
    "
    2.22
    While
    2.22
    as
    2.20
    //
    2.08
    Then
    2.06
    Who
    2.03
    <em>
    2.02
    Activations Density 0.004%

    No Known Activations