© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41931
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ?
    0.48
    @
    0.46
     /
    0.44
    /
    0.44
     was
    0.44
    cation
    0.44
    [
    0.43
    +
    0.42
     ,
    0.42
     have
    0.42
    POSITIVE LOGITS
     formulario
    0.50
     выполнение
    0.50
     formularios
    0.49
     Марафон
    0.48
     instrucción
    0.47
     tarefas
    0.46
     લાભ
    0.46
     laurea
    0.46
     формы
    0.46
     नौकरी
    0.45
    Activations Density 0.015%

    No Known Activations