© 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. 32011
    Prev
    Next
    INDEX
    Explanations

    rolled 'r' or straight leg raise

    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
    舘
    0.51
     meinen
    0.49
    浴室
    0.48
    潅
    0.46
     डेली
    0.44
    ধিক
    0.42
    glichen
    0.41
    kepsilon
    0.41
    䛺
    0.41
    ffine
    0.41
    POSITIVE LOGITS
     bott
    0.44
     exports
    0.40
     Phoenix
    0.39
     draft
    0.39
     Portal
    0.38
     apps
    0.37
     attractions
    0.37
     CMS
    0.37
     once
    0.37
     Sem
    0.36
    Activations Density 0.000%

    No Known Activations