© 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. 41931
    Prev
    Next
    INDEX
    Explanations

    numbers, punctuation, and specific entities

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

    forms and tasks

    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
    /
    0.50
    ?
    0.49
    @
    0.49
    +
    0.46
     /
    0.45
    ;-
    0.45
    cation
    0.45
    "
    0.45
    ;
    0.44
    ’
    0.43
    POSITIVE LOGITS
     выполнение
    0.58
     расходы
    0.52
     Марафон
    0.51
     машинасы
    0.51
     инструкции
    0.49
     பயிற்
    0.48
    ваемых
    0.48
     подчи
    0.48
     да
    0.48
     preparazione
    0.48
    Activations Density 0.000%

    No Known Activations