© 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. 18056
    Prev
    Next
    INDEX
    Explanations

    Each item in a collection

    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
    $
    0.47
    Мі
    0.46
     unsuitable
    0.45
    Ꮯ
    0.45
     awọn
    0.45
     ndị
    0.44
     redundancies
    0.43
    एफसी
    0.43
     manures
    0.43
    ソ
    0.42
    POSITIVE LOGITS
     Each
    0.61
    Each
    0.53
     每个
    0.52
     Once
    0.47
    у
    0.46
     sentado
    0.45
    represents
    0.44
     einzelne
    0.44
     varje
    0.44
     jeder
    0.43
    Activations Density 0.034%

    No Known Activations