© 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. 211008
    Prev
    Next
    INDEX
    Explanations

    installed into

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

    limit enforced

    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
    屽
    0.52
     marginTop
    0.50
    🖌
    0.45
     ntawm
    0.44
     माणसा
    0.44
    ローバル
    0.44
     માર
    0.44
    ittarius
    0.44
    ell
    0.44
    ங்கம்
    0.43
    POSITIVE LOGITS
    GH
    0.54
    tv
    0.50
    IST
    0.49
    STEM
    0.49
     ಡ
    0.49
    STEN
    0.49
    ZA
    0.49
    OSP
    0.49
    DRO
    0.49
    OC
    0.48
    Activations Density 0.001%

    No Known Activations