© 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. 40-GEMMASCOPE-2-RES-262K
    7. 119437
    Prev
    Next
    INDEX
    Explanations

    app lifecycle methods

    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
    Ⴀ
    0.39
    ᖅ
    0.39
    리티
    0.39
     diretto
    0.38
    ⼯
    0.38
     coinbase
    0.38
     east
    0.37
     $(
    0.37
    აკ
    0.37
    音樂
    0.37
    POSITIVE LOGITS
    oyen
    0.40
    astaan
    0.40
    ects
    0.39
    ques
    0.38
    inergic
    0.36
    ఖా
    0.36
    idents
    0.36
     Lij
    0.36
    Linked
    0.36
    ໃຫ
    0.35
    Activations Density 0.002%

    No Known Activations