© 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. 224362
    Prev
    Next
    INDEX
    Explanations

    copying as punishment

    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
    耘
    0.44
     الآ
    0.41
     hemat
    0.40
     Fuel
    0.40
     przyp
    0.39
     Aa
    0.39
     hacía
    0.38
     solicitud
    0.38
     femora
    0.38
    蘼
    0.38
    POSITIVE LOGITS
    your
    0.45
    thand
    0.43
    HTML
    0.42
    vou
    0.41
    sef
    0.40
    iteration
    0.40
    찍
    0.40
    igueur
    0.39
    optimize
    0.39
    ligne
    0.39
    Activations Density 0.000%

    No Known Activations