© 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. 36724
    Prev
    Next
    INDEX
    Explanations

    All Fire

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

    words before or after specific tokens

    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
    invest
    0.50
    an
    0.49
     Продол
    0.49
     наи
    0.47
    Arte
    0.46
     آرام
    0.44
     Parte
    0.44
     ប
    0.44
     initially
    0.44
     הא
    0.44
    POSITIVE LOGITS
    ্নে
    0.50
    elementType
    0.49
    تقديم
    0.46
    ’।
    0.45
    🚩
    0.44
    숲
    0.44
     मौजूदगी
    0.43
     grandson
    0.43
     সমর্থনে
    0.43
    ਗੇ
    0.43
    Activations Density 0.000%

    No Known Activations