© 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. 44996
    Prev
    Next
    INDEX
    Explanations

    stories, inventions, science, art

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

    persistent issues

    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
    log
    0.50
    migrate
    0.48
    data
    0.46
     migrated
    0.46
     comorbid
    0.46
     plummeted
    0.45
    exported
    0.45
    f
    0.44
    as
    0.44
    lived
    0.44
    POSITIVE LOGITS
    䍘
    0.55
     فإن
    0.50
     ইহাতে
    0.49
    美术
    0.49
     미술
    0.48
     Collage
    0.48
    玑
    0.48
     permettent
    0.48
    ഞ
    0.47
    梸
    0.46
    Activations Density 0.000%

    No Known Activations