© 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-65K
    7. 65037
    Prev
    Next
    INDEX
    Explanations

    parameters, IDs, Walmart, errors

    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_65k_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
    ISK
    0.46
    pple
    0.42
     पाणी
    0.41
     sebagian
    0.41
     ย
    0.41
     ي
    0.39
     separation
    0.39
    ítja
    0.39
    K
    0.39
    iva
    0.39
    POSITIVE LOGITS
    चु
    0.52
     classe
    0.48
    拶
    0.47
     tcpHeader
    0.46
    প্রাচ
    0.46
     giovane
    0.46
    耷
    0.45
     punctatis
    0.45
     chiese
    0.45
    ברת
    0.45
    Activations Density 0.006%

    No Known Activations