© 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. 106926
    Prev
    Next
    INDEX
    Explanations

    access modifiers like public

    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
     while
    -0.94
    ciclopedia
    -0.91
     בשנת
    -0.91
     whereby
    -0.89
     Aussage
    -0.87
     since
    -0.87
    íně
    -0.87
    Ƚ
    -0.86
     ネックレス
    -0.85
    niaus
    -0.84
    POSITIVE LOGITS
    public
    1.40
     public
    1.26
     private
    1.03
    private
    0.93
     Ν
    0.86
    cosity
    0.84
     metod
    0.84
     sólo
    0.82
     your
    0.82
     intende
    0.81
    Activations Density 0.012%

    No Known Activations