© 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. 219541
    Prev
    Next
    INDEX
    Explanations

    numbers followed by times or addresses

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

    processing large amounts of text data

    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
    Dirt
    0.51
     Dirt
    0.48
    ORTYPE
    0.47
     ヨ
    0.44
    OLYBDENUM
    0.44
    >`;
    0.43
    ARIFF
    0.43
    '>";
    0.42
     hydrology
    0.42
     parishes
    0.41
    POSITIVE LOGITS
    of
    0.56
    ing
    0.53
    faux
    0.50
     assol
    0.48
    érences
    0.48
    añas
    0.47
    ensi
    0.46
    ed
    0.46
     абсолютно
    0.45
    er
    0.45
    Activations Density 0.000%

    No Known Activations