© 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. 43269
    Prev
    Next
    INDEX
    Explanations

    numbers and code

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

    numbers and quantities

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ારો
    0.26
    孟
    0.26
    ശാ
    0.25
    ت
    0.25
     حس
    0.25
     ദിവ
    0.25
    சே
    0.25
    すぎる
    0.25
     પોતાની
    0.25
    据悉
    0.25
    POSITIVE LOGITS
     fillets
    0.28
     vertices
    0.28
     eleven
    0.28
     সংখ্যাগরিষ্ঠ
    0.27
     floc
    0.26
    分成
    0.26
    5
    0.25
     thirteen
    0.25
     pią
    0.25
     STRU
    0.25
    Activations Density 0.041%

    No Known Activations