© 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. 174892
    Prev
    Next
    INDEX
    Explanations

    locations and foreign languages

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

    geometric properties or celestial bodies

    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
     microns
    0.47
     kr
    0.47
    co
    0.46
     sehe
    0.45
    com
    0.45
     highs
    0.44
     sequester
    0.44
    z
    0.43
     sequ
    0.43
     beg
    0.42
    POSITIVE LOGITS
     лінії
    0.47
    '=
    0.46
    '!
    0.44
     러
    0.43
     歩
    0.43
     шриф
    0.43
    োঁয়া
    0.42
    均匀
    0.42
    🚋
    0.42
     уни
    0.42
    Activations Density 0.000%

    No Known Activations