© 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. 16698
    Prev
    Next
    INDEX
    Explanations

    sports statistics and business plans

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

    `fn main`, REM, csv

    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
    ነ
    0.47
    チラ
    0.46
    핀
    0.46
    보
    0.46
    די
    0.46
    ワイ
    0.44
    ופ
    0.44
    SER
    0.43
     reusable
    0.42
    使
    0.41
    POSITIVE LOGITS
     escolas
    0.53
     mengadakan
    0.50
     ơi
    0.47
     sviluppo
    0.46
     déficit
    0.46
     tertentu
    0.46
     bénéficier
    0.46
     scuole
    0.46
     ४
    0.46
     fortal
    0.45
    Activations Density 0.000%

    No Known Activations