© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 31831
    Prev
    Next
    INDEX
    Explanations

    shared module configurations

    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_16_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
    ’
    0.63
    for
    0.62
     itd
    0.59
    p
    0.56
    '
    0.55
     \
    0.54
    \
    0.53
    center
    0.53
    ż
    0.52
     detener
    0.50
    POSITIVE LOGITS
     landlab
    0.61
     imperatives
    0.61
     spindles
    0.60
     Ecusson
    0.57
    ியை
    0.56
    EIN
    0.54
     Gujarati
    0.54
     zaji
    0.54
     चव्हाण
    0.54
    的美
    0.54
    Activations Density 0.002%

    No Known Activations