© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 96531
    Prev
    Next
    INDEX
    Explanations

    accepted papers, volunteer for

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

    special characters and succeeding words

    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
     κύ
    0.42
    藁
    0.42
     udf
    0.42
     removes
    0.41
    去除
    0.41
    クリー
    0.41
     whereupon
    0.40
     daarbij
    0.40
     rul
    0.40
    舧
    0.39
    POSITIVE LOGITS
    unum
    0.53
     Одна
    0.53
    wang
    0.53
    Одна
    0.53
    illen
    0.50
    ಧಾರವಾಡ
    0.49
    graphic
    0.48
    shiny
    0.47
    javafx
    0.47
    Sp
    0.46
    Activations Density 0.001%

    No Known Activations