© 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. 233468
    Prev
    Next
    INDEX
    Explanations

    option and date specific criteria

    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
     pptd
    0.52
    ্যোগ
    0.52
    ᱷ
    0.49
    داشت
    0.49
     indignation
    0.48
    ிருந்தார்
    0.47
    اریخ
    0.47
     outraged
    0.47
     grievous
    0.47
     Keynes
    0.46
    POSITIVE LOGITS
    part
    0.52
    chemical
    0.51
    function
    0.51
     in
    0.50
    th
    0.50
    go
    0.50
    k
    0.49
    (
    0.49
    close
    0.48
    pack
    0.48
    Activations Density 0.002%

    No Known Activations