© 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. 30757
    Prev
    Next
    INDEX
    Explanations

    representar jerarquías o relaciones

    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
     comercial
    0.35
    fand
    0.35
     threx
    0.34
     Fab
    0.34
    <s>
    0.33
     @
    0.33
     x
    0.33
     Festival
    0.33
     xi
    0.33
    なければ
    0.33
    POSITIVE LOGITS
    منى
    0.40
    aszt
    0.40
    基地
    0.39
    ಾತ
    0.39
    indazole
    0.39
    Ầ
    0.39
    㬹
    0.38
    CommandHandler
    0.38
     ঘটনাস্থ
    0.38
    བ་
    0.38
    Activations Density 0.000%

    No Known Activations