© 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. 78944
    Prev
    Next
    INDEX
    Explanations

    package management and links

    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
    LinearLayout
    -0.82
    బ
    -0.73
    inline
    -0.72
     passada
    -0.72
    from
    -0.71
    Yue
    -0.71
     Oleg
    -0.70
     submarines
    -0.69
    Linq
    -0.69
     espíritu
    -0.69
    POSITIVE LOGITS
     Don
    0.78
    genti
    0.73
     Never
    0.72
    No
    0.72
    ñ
    0.72
     No
    0.71
    allowNull
    0.67
    NotNull
    0.67
     सद
    0.66
    vais
    0.65
    Activations Density 0.429%

    No Known Activations