© 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. 84751
    Prev
    Next
    INDEX
    Explanations

    crimes, harms, codec, parallel

    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
     in
    0.54
     alt
    0.50
     Innovation
    0.49
     Hurd
    0.49
    ’
    0.48
     ident
    0.47
     innov
    0.46
     Journals
    0.46
     고민
    0.46
     Clin
    0.45
    POSITIVE LOGITS
    𒍪
    0.57
    થમ
    0.50
     rapaz
    0.47
    生の
    0.47
    gaxModule
    0.46
    DeferredGroup
    0.46
    
    0.46
    対訳
    0.46
     demuestra
    0.46
     χωρίς
    0.45
    Activations Density 0.001%

    No Known Activations