© 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. 241677
    Prev
    Next
    INDEX
    Explanations

    needs, eyes, fiber, this is

    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
    וט
    0.49
    T
    0.48
    வ்
    0.48
    ง
    0.47
    ަރު
    0.46
    어
    0.43
    된
    0.43
    भा
    0.42
     cavalry
    0.42
    वला
    0.42
    POSITIVE LOGITS
    AvlTree
    0.57
     gxf
    0.55
    xgb
    0.50
    lyrics
    0.49
    kmeans
    0.49
    GTUIKit
    0.48
    poetry
    0.48
     リュ
    0.48
     言っ
    0.48
     habló
    0.47
    Activations Density 0.007%

    No Known Activations