Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 247425
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Μ
    0.56
    м
    0.50
    ;
    0.48
     m
    0.48
    г
    0.48
    פי
    0.47
    Ч
    0.46
    MS
    0.46
    年的
    0.46
    Ç
    0.45
    POSITIVE LOGITS
     onboarding
    0.53
     निशुल्क
    0.49
     Accreditation
    0.46
     informée
    0.45
    园区
    0.45
     Timeline
    0.44
     Toolkit
    0.44
     enablement
    0.43
     accreditation
    0.43
     canad
    0.43
    Activations Density 0.009%

    No Known Activations