© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21487
    Prev
    Next
    INDEX
    Explanations

    abstract and virtual methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    俳優
    0.50
     косми
    0.47
    ஆம்
    0.46
     комитета
    0.45
     ढांचे
    0.44
    原料
    0.43
     металли
    0.43
     и
    0.42
     आणि
    0.42
    ছিলাম
    0.42
    POSITIVE LOGITS
    getHeight
    0.47
    idir
    0.47
    ەک
    0.46
    tsó
    0.43
    ateness
    0.42
    getIndex
    0.42
    getRadius
    0.42
    ünün
    0.42
    åd
    0.42
     INDEX
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.