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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92238
    Prev
    Next
    INDEX
    Explanations

    programming keywords: public, protected, const, init

    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
    default
    -0.88
     générales
    -0.85
     凉
    -0.84
     Ellos
    -0.83
     zdjęcie
    -0.82
    void
    -0.82
     default
    -0.81
     Versorgung
    -0.81
     många
    -0.81
    apolis
    -0.81
    POSITIVE LOGITS
    public
    1.18
    explicit
    1.02
     heutige
    0.97
     is
    0.92
     explicit
    0.85
     생성
    0.83
     грудь
    0.81
    是多少
    0.79
     what
    0.79
     heutigen
    0.79
    Activations Density 0.015%

    No Known Activations