© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 14289
    Prev
    Next
    INDEX
    Explanations

    whether introducing alternatives

    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
    م
    0.86
    ق
    0.82
    ج
    0.81
    m
    0.74
    t
    0.72
     all
    0.68
     anything
    0.67
     różne
    0.67
    هم
    0.66
     There
    0.66
    POSITIVE LOGITS
    '
    0.71
    го
    0.70
    rá
    0.67
    я
    0.66
    ță
    0.65
    ky
    0.63
    are
    0.63
    ţă
    0.63
    ana
    0.61
    isiin
    0.61
    Activations Density 0.023%

    No Known Activations