© 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. 249742
    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
    *
    0.54
     método
    0.46
     cara
    0.44
    し
    0.44
     shaft
    0.44
     coloc
    0.43
    salaryfrom
    0.43
     metoda
    0.42
    (
    0.42
    ramento
    0.41
    POSITIVE LOGITS
     Playoffs
    0.50
    NBC
    0.48
     Prozent
    0.48
    צ
    0.47
     Aesthetics
    0.45
     Iterable
    0.44
     बारह
    0.44
    ập
    0.44
    牞
    0.43
    墘
    0.43
    Activations Density 0.003%

    No Known Activations