© 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. 97121
    Prev
    Next
    INDEX
    Explanations

    reported to, one of, city guide

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

    line width

    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
     irrigated
    0.54
     vigente
    0.51
    -
    0.48
     Alpine
    0.48
     tensión
    0.47
    igation
    0.45
     Lakewood
    0.45
    atin
    0.45
     ceiling
    0.45
    冰
    0.45
    POSITIVE LOGITS
     たい
    0.51
    ıları
    0.50
    碖
    0.49
     நிகழ்
    0.47
     아마
    0.47
     самую
    0.47
     bruta
    0.47
     Lernen
    0.47
    ᒫ
    0.47
    eud
    0.45
    Activations Density 0.000%

    No Known Activations