© 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. 209057
    Prev
    Next
    INDEX
    Explanations

    words or phrases discussing time, materials, or specific items like flooring, EPR, or sale

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

    instructional language

    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
    ཿ
    0.51
    పర్
    0.48
    يله
    0.44
    Nft
    0.44
    ند
    0.44
    تي
    0.43
    বের
    0.43
    يد
    0.43
     Здесь
    0.42
    蕖
    0.42
    POSITIVE LOGITS
     aps
    0.50
     Geno
    0.48
     aplic
    0.48
     systemu
    0.48
     structural
    0.46
     stos
    0.46
     polio
    0.45
     ak
    0.44
    asts
    0.44
     ats
    0.44
    Activations Density 0.009%

    No Known Activations