© 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. 22869
    Prev
    Next
    INDEX
    Explanations

    needs provided play impact half

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

    reading files and service

    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
    adería
    0.48
    न्या
    0.47
     конкур
    0.46
    poetrycommunity
    0.45
    㳒
    0.43
    ワク
    0.43
     ఆధ్యాత్మిక
    0.42
     конку
    0.42
    UIAlert
    0.42
    ceptar
    0.42
    POSITIVE LOGITS
     numerous
    0.52
     Davis
    0.46
     MPs
    0.46
     Mitchell
    0.46
     Bennett
    0.45
     Omar
    0.45
     Klein
    0.45
    ↵
    0.44
    ">
    0.44
     strong
    0.44
    Activations Density 0.000%

    No Known Activations