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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118958
    Prev
    Next
    INDEX
    Explanations

    public vs private visibility

    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
     obiek
    -0.80
    Swipe
    -0.79
     Vereinigung
    -0.76
    enservice
    -0.76
    pylene
    -0.73
    厝
    -0.73
    KI
    -0.72
    eternal
    -0.70
    乾
    -0.70
    Unused
    -0.69
    POSITIVE LOGITS
     visibility
    2.33
     privacy
    2.16
     private
    2.03
    visibility
    2.00
     public
    1.88
    Visibility
    1.86
    private
    1.84
     Visibility
    1.84
    setVisibility
    1.83
     PRIVATE
    1.78
    Activations Density 0.074%

    No Known Activations