© 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. 100502
    Prev
    Next
    INDEX
    Explanations

    always, will, situation, dumpster, fantastic

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

    data preprocessing and transformation

    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
    開発
    0.55
    <0xA9>
    0.51
     Novak
    0.47
     pearl
    0.47
     Nakam
    0.47
    тился
    0.46
    gul
    0.45
     privat
    0.44
    業
    0.44
     bordering
    0.44
    POSITIVE LOGITS
    """
    0.55
    """,
    0.55
    hamming
    0.50
    "",
    0.47
    。,
    0.46
    """"
    0.46
    hna
    0.46
     QuantityOnHand
    0.46
     resTmp
    0.45
     ermöglicht
    0.45
    Activations Density 0.001%

    No Known Activations