© 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. 181656
    Prev
    Next
    INDEX
    Explanations

    foreign words

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

    business, POS, query, TVs, number

    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
    츈
    0.51
    },-
    0.48
    methylation
    0.47
    optosis
    0.45
    widet
    0.44
     Incidentally
    0.44
    alassemia
    0.44
     Ото
    0.44
     ஏற்பட்டு
    0.43
     NSUTF
    0.43
    POSITIVE LOGITS
     jejich
    0.46
     város
    0.46
    闖
    0.46
     bakan
    0.43
     keç
    0.43
    他们的
    0.43
    เท้า
    0.42
    رجال
    0.42
    スタン
    0.41
     onların
    0.41
    Activations Density 0.001%

    No Known Activations