© 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. 40862
    Prev
    Next
    INDEX
    Explanations

    attention-grabbing emojis

    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
    ъл
    0.56
    га
    0.54
    р
    0.54
    गमेंट
    0.53
    пи
    0.51
    সাম
    0.50
     نیک
    0.50
    ذ
    0.49
     아닌
    0.49
    そも
    0.48
    POSITIVE LOGITS
    :
    0.87
    -
    0.82
    ’
    0.71
    4
    0.67
    5
    0.64
    8
    0.62
    7
    0.62
    on
    0.61
     consente
    0.56
    ↵↵
    0.56
    Activations Density 0.017%

    No Known Activations