© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56672
    Prev
    Next
    INDEX
    Explanations

    phrases ending in punctuation

    np_acts-logits-general · gemini-2.5-flash-lite

    special characters and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    on
    1.05
    ها
    1.00
    သောအ
    0.92
    ON
    0.90
    ي
    0.86
    am
    0.83
    la
    0.82
    that
    0.81
    şey
    0.79
    те
    0.79
    POSITIVE LOGITS
     únic
    0.74
     kinderen
    0.70
     servants
    0.70
     ۶
    0.68
     zy
    0.67
     부터
    0.67
     마
    0.66
     ២
    0.66
     집에
    0.66
    孩子
    0.65
    Activations Density 0.147%

    No Known Activations