© 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. 202164
    Prev
    Next
    INDEX
    Explanations

    following customer

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

    activities, quickly, relate, based, inputs

    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
     Taj
    0.49
    入門
    0.44
     dépasse
    0.44
     페
    0.43
    三十
    0.42
     Peshawar
    0.42
     Northwestern
    0.42
     Ugandan
    0.41
     Krypt
    0.40
     доби
    0.39
    POSITIVE LOGITS
    locals
    0.49
    सरकार
    0.49
     સરકાર
    0.47
     trataro
    0.47
    코
    0.47
    श्यक
    0.46
     locals
    0.45
     preconditions
    0.45
    ừa
    0.45
    لى
    0.45
    Activations Density 0.001%

    No Known Activations