© 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. 97479
    Prev
    Next
    INDEX
    Explanations

    fraction representation

    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
    。(
    0.59
    ’
    0.57
     diffusing
    0.56
    '।
    0.55
    L
    0.53
    ।
    0.52
    را
    0.51
    ING
    0.50
    atau
    0.50
    of
    0.50
    POSITIVE LOGITS
    其他
    0.69
     আরও
    0.61
    ه
    0.60
     অন্যান্য
    0.57
    ä
    0.57
    ğini
    0.56
    śmy
    0.54
    一个新的
    0.52
    ći
    0.52
     Thieves
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.