© 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. 239051
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation

    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
    すると
    0.47
    ٺ
    0.47
    Ժ
    0.46
    あって
    0.46
    市政府
    0.45
    公園
    0.45
    CONH
    0.44
    Ｊ
    0.44
    Ⲕ
    0.44
    月から
    0.44
    POSITIVE LOGITS
     >>>
    0.54
    <<<
    0.53
    ierte
    0.52
    amat
    0.52
    them
    0.50
    tls
    0.49
     Underlying
    0.49
    <<<<
    0.48
     <<<
    0.48
     <<
    0.46
    Activations Density 0.000%

    No Known Activations