© 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. 50893
    Prev
    Next
    INDEX
    Explanations

    elegant dinner, island, catalog, mode, Friday, signature, spect-acular monster

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

    Docker Compose, zip archive, lost things

    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
     National
    0.48
    al
    0.46
    ست
    0.46
    خ
    0.46
     coffee
    0.45
     Coffee
    0.45
    نے
    0.45
     asylum
    0.45
    atina
    0.45
     Hol
    0.44
    POSITIVE LOGITS
    ’),
    0.49
    ==(
    0.49
    뺄
    0.49
     体
    0.48
     ნაკ
    0.48
     ቀላል
    0.48
     እንቅ
    0.47
     取っ
    0.47
    뺏
    0.47
     代表
    0.47
    Activations Density 0.000%

    No Known Activations