© 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. 32059
    Prev
    Next
    INDEX
    Explanations

    Majors, Islands, Avion, Diabetes, Barron, http, aisles, Auditor

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

    purpose of questions

    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
    k
    0.57
    successor
    0.55
    URAL
    0.54
    khar
    0.54
    sman
    0.54
    ka
    0.52
    kk
    0.52
    klär
    0.51
    ULATIONS
    0.51
    a
    0.51
    POSITIVE LOGITS
     Majors
    0.50
     tags
    0.46
     Islands
    0.46
     Avion
    0.46
     Diabetes
    0.45
     Barron
    0.45
     http
    0.45
     aisles
    0.45
     &.
    0.45
     Auditor
    0.44
    Activations Density 0.000%

    No Known Activations