© 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. 102245
    Prev
    Next
    INDEX
    Explanations

    web hosting and email services

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

    hosting and email services

    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
     аку
    0.44
    years
    0.40
     оли
    0.40
    뱃
    0.40
    大型
    0.39
     acoustic
    0.39
     acoust
    0.39
    स्थित
    0.39
    襲
    0.39
    เสียง
    0.38
    POSITIVE LOGITS
    িয়ন
    0.43
     maíz
    0.42
     missionaries
    0.40
     Pestic
    0.40
     Cómo
    0.40
    iapan
    0.39
     Crops
    0.39
     Brew
    0.39
     esquina
    0.39
    Mail
    0.38
    Activations Density 0.064%

    No Known Activations