© 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. 34911
    Prev
    Next
    INDEX
    Explanations

    rectal fluids, mixture of experts

    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
     /.
    0.45
     Белару
    0.45
    र्नल
    0.44
    Criteria
    0.44
     РФ
    0.43
     Беларусі
    0.43
    ürlich
    0.43
     atualizar
    0.43
    Criterion
    0.42
     अंग्रेजों
    0.42
    POSITIVE LOGITS
    ak
    0.49
    i
    0.47
    ha
    0.47
    sess
    0.46
    born
    0.45
    ts
    0.45
    last
    0.43
    in
    0.43
    sen
    0.43
     Vi
    0.42
    Activations Density 0.003%

    No Known Activations