© 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. 245622
    Prev
    Next
    INDEX
    Explanations

    family names and relationships

    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
     incentives
    0.45
     Sawyer
    0.44
    amp
    0.43
     experience
    0.43
     agreeing
    0.43
    肯
    0.43
    ":
    0.43
    더
    0.42
    和我
    0.42
     Harwell
    0.42
    POSITIVE LOGITS
     በተጨማሪ
    0.58
    ografie
    0.50
     భారతదేశ
    0.45
    Ẹ
    0.43
     እንዲሁም
    0.43
     イタリア
    0.42
    瀉
    0.42
     முதுகு
    0.42
    blooded
    0.42
     frigor
    0.42
    Activations Density 0.000%

    No Known Activations