© 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. 113466
    Prev
    Next
    INDEX
    Explanations

    financial loan services

    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
    on
    -2.19
    絰
    -2.14
    🤮
    -1.92
    ⁉
    -1.86
    😂😂😂😂
    -1.86
     narra
    -1.84
    🖕
    -1.82
    ✔️
    -1.77
     carrefour
    -1.74
    ✅
    -1.74
    POSITIVE LOGITS
     that
    2.23
     übri
    2.14
    pecabe
    2.13
     znajdu
    2.13
     vorhand
    2.09
    नलोड
    2.08
     naszego
    1.97
     gutes
    1.96
    锜
    1.94
     Kenntnis
    1.92
    Activations Density 0.028%

    No Known Activations