© 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. 102977
    Prev
    Next
    INDEX
    Explanations

    public, protected, function

    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
     @
    -1.42
    @
    -1.08
    ...@
    -1.05
    (@
    -0.99
     @$
    -0.90
    \@
    -0.89
    ounds
    -0.85
    ᚖ
    -0.83
    issent
    -0.82
     cwd
    -0.81
    POSITIVE LOGITS
     function
    1.10
     public
    1.00
    public
    0.92
    function
    0.91
     pubblico
    0.79
     Tides
    0.79
     públicos
    0.77
    protected
    0.75
     thật
    0.74
     अलावा
    0.73
    Activations Density 0.003%

    No Known Activations