© 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. 243474
    Prev
    Next
    INDEX
    Explanations

    resources to schedule for lack

    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
     monster
    0.50
    א
    0.48
     informazioni
    0.47
    каде
    0.46
    超級
    0.46
     cookie
    0.42
    Ста
    0.41
    ทราบ
    0.41
     stallion
    0.41
     sausage
    0.39
    POSITIVE LOGITS
    appoint
    0.50
     you
    0.49
    giờ
    0.49
     போதும்
    0.49
    Scan
    0.46
     городской
    0.46
    🎺
    0.46
     giờ
    0.45
    ্ে
    0.44
    তুমি
    0.44
    Activations Density 0.001%

    No Known Activations