© 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. 30276
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation separators

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

    function calls and arguments

    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
    事で
    0.50
     সব্ব
    0.46
     सगळ्या
    0.44
    ото
    0.43
    作る
    0.41
     Continuando
    0.41
     सांगतात
    0.40
    巻
    0.39
    扉
    0.39
     равна
    0.39
    POSITIVE LOGITS
    idcoin
    0.42
     liqu
    0.40
    Toggle
    0.39
    textup
    0.39
    ͅ
    0.39
     semia
    0.38
    glClear
    0.38
    lastval
    0.36
    ज्ञा
    0.36
    SetActive
    0.36
    Activations Density 0.004%

    No Known Activations