© 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. 151652
    Prev
    Next
    INDEX
    Explanations

    person or entity

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

    plan to obtaining

    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
     Bola
    0.46
     Bóng
    0.46
    ص
    0.44
    सूत्र
    0.43
     కి
    0.43
     Contador
    0.43
    ↵
    0.42
     Nä
    0.42
    عة
    0.41
     Counsel
    0.41
    POSITIVE LOGITS
    ikoa
    0.46
     アイアン
    0.45
    san
    0.44
     যতটা
    0.44
    štění
    0.44
    イオン
    0.43
     pensado
    0.43
    rta
    0.43
    trz
    0.42
    ➛
    0.42
    Activations Density 0.001%

    No Known Activations