© 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. 8918
    Prev
    Next
    INDEX
    Explanations

    Gaussian blur, kernel size, sigma

    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
     команд
    0.54
    。
    0.52
    и
    0.50
     EditText
    0.50
    п
    0.49
    ک
    0.49
    =".
    0.48
    সঙ্গে
    0.48
    。"
    0.48
    ტ
    0.48
    POSITIVE LOGITS
     toplum
    0.50
     terem
    0.49
     hätten
    0.47
     goû
    0.47
     liya
    0.46
     wal
    0.45
     morgen
    0.45
     hati
    0.44
     श्रद्धालुओं
    0.43
     laufen
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.