© 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. 75829
    Prev
    Next
    INDEX
    Explanations

    private browsing and incognito tabs

    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
    ENSEN
    -0.81
     Babel
    -0.76
    hetic
    -0.76
    ysan
    -0.75
     huu
    -0.73
    isAdmin
    -0.71
    addComponent
    -0.71
     Sons
    -0.70
    PRIM
    -0.69
    ⌬
    -0.69
    POSITIVE LOGITS
    cognito
    1.87
     private
    1.86
     Private
    1.57
     disguise
    1.53
    Private
    1.49
    private
    1.45
     privaten
    1.38
     anonymous
    1.36
     disguised
    1.36
    PRIVATE
    1.20
    Activations Density 0.038%

    No Known Activations