© 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. 40913
    Prev
    Next
    INDEX
    Explanations

    https:// download Epub download

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

    non-english language characters

    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
    enders
    0.54
    lé
    0.53
     exorbit
    0.52
    ths
    0.49
    this
    0.48
    lt
    0.47
    riers
    0.46
    0
    0.46
    rsa
    0.46
    river
    0.45
    POSITIVE LOGITS
    蕖
    0.56
    戞
    0.54
    ಾದರೆ
    0.52
     ചരി
    0.49
    িণ
    0.48
    িকা
    0.47
    呿
    0.47
    Kalau
    0.47
    ార్క్
    0.47
    クリー
    0.46
    Activations Density 0.000%

    No Known Activations