© 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. 61960
    Prev
    Next
    INDEX
    Explanations

    works or continues

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

    natural flow and description

    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
    珲
    0.49
     함수
    0.48
     идеи
    0.46
     timelapse
    0.46
    崩溃
    0.45
     这个
    0.44
     Ressourcen
    0.44
    相關文章
    0.44
     Funktionen
    0.44
     hücre
    0.44
    POSITIVE LOGITS
    🅱
    0.46
     Yankees
    0.46
    ibs
    0.44
     Kentucky
    0.44
    }
    0.43
    idic
    0.43
     those
    0.42
    ậm
    0.41
    純正
    0.41
     thoroughly
    0.41
    Activations Density 0.000%

    No Known Activations