© 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. 168450
    Prev
    Next
    INDEX
    Explanations

    thread starter:

    np_acts-logits-general · gemini-2.5-flash-lite

    underlying cause or tumor

    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
    нике
    0.54
    тво
    0.52
    したり
    0.52
     sensory
    0.50
    нын
    0.47
     blinking
    0.47
    ґ
    0.46
    ле
    0.46
     후
    0.46
     ისინი
    0.46
    POSITIVE LOGITS
    H
    0.91
    M
    0.83
    T
    0.82
    W
    0.82
    K
    0.79
    B
    0.78
    N
    0.76
    ל
    0.74
    X
    0.73
    R
    0.73
    Activations Density 0.001%

    No Known Activations