© 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. 29771
    Prev
    Next
    INDEX
    Explanations

    associated with concepts

    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_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
     学校
    0.50
    Გ
    0.49
     जम
    0.48
    obile
    0.48
    schools
    0.48
     Arbe
    0.47
    Archivo
    0.47
     रहेगा
    0.47
    Servers
    0.47
    usehen
    0.47
    POSITIVE LOGITS
     (
    0.49
     boutique
    0.44
    াধি
    0.39
     valuation
    0.39
     benefactor
    0.38
    0.38
     league
    0.37
     রাতে
    0.37
     XXL
    0.37
     locale
    0.37
    Activations Density 0.000%

    No Known Activations