© 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. 182740
    Prev
    Next
    INDEX
    Explanations

    cadastral surveys, interior, why, books, DOI, crucial

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

    and creates

    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
    器的
    0.47
     CUSTOM
    0.46
    לה
    0.46
     COLL
    0.45
     yad
    0.45
    VILLE
    0.44
     personnalisé
    0.44
    彌
    0.43
     STAND
    0.43
     올
    0.43
    POSITIVE LOGITS
    atka
    0.48
     subdued
    0.47
    spath
    0.47
    membrane
    0.47
     dopamine
    0.46
    attha
    0.45
     rained
    0.45
     brine
    0.45
     carbonic
    0.45
     sulphuric
    0.45
    Activations Density 0.000%

    No Known Activations