© 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. 57439
    Prev
    Next
    INDEX
    Explanations

    private method declarations

    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
    entikan
    -0.84
     ||=
    -0.82
     entregó
    -0.79
    𝙲
    -0.77
    ?}",
    -0.77
     Estable
    -0.77
    regelen
    -0.77
     kandid
    -0.76
    ℅
    -0.76
    atrici
    -0.76
    POSITIVE LOGITS
    void
    1.84
     void
    1.71
    private
    1.09
     private
    1.01
    Private
    0.97
    )‏
    0.91
    XMLSchema
    0.90
    uary
    0.90
    dega
    0.89
    موس
    0.88
    Activations Density 0.002%

    No Known Activations