© 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. 30621
    Prev
    Next
    INDEX
    Explanations

    All Rights Reserved

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

    searching the web

    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
     kan
    0.50
    erit
    0.49
    _
    0.46
    airline
    0.44
    erat
    0.44
     them
    0.44
    anskrit
    0.43
    olina
    0.43
    kan
    0.43
    outheast
    0.43
    POSITIVE LOGITS
    Mama
    0.47
    主な
    0.46
    鹊
    0.44
     жүкт
    0.43
     कमाई
    0.43
    xxxxxxxx
    0.43
    愷
    0.43
     Steuer
    0.42
     геометри
    0.42
    🤍
    0.42
    Activations Density 0.000%

    No Known Activations