© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 110905
    Prev
    Next
    INDEX
    Explanations

    historical timeline

    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_40_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
    ਿਸ
    0.45
    厢
    0.41
    coat
    0.40
    Included
    0.40
    ᱗
    0.39
    rbac
    0.39
    ahlt
    0.38
     компонентов
    0.38
    Insight
    0.38
     покрытия
    0.38
    POSITIVE LOGITS
    齡
    0.38
     Stephanie
    0.38
     offspring
    0.37
     erscheint
    0.37
     pm
    0.37
     philosopher
    0.37
    ዛት
    0.37
     heart
    0.36
     draped
    0.36
     midnight
    0.36
    Activations Density 0.000%

    No Known Activations