Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 19925
    Prev
    Next
    INDEX
    Explanations

    pointless metric

    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
     HK
    0.39
    볐
    0.38
    Thing
    0.37
    Introduction
    0.37
     JK
    0.36
     LK
    0.36
    早在
    0.36
    없
    0.36
    ূল্যে
    0.36
    HK
    0.35
    POSITIVE LOGITS
     AGAIN
    0.41
     lại
    0.39
     furn
    0.38
     Florida
    0.37
     italiane
    0.37
    гре
    0.37
     distracting
    0.37
    ⿸
    0.36
     புரி
    0.35
    RELAND
    0.35
    Activations Density 0.000%

    No Known Activations