© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 155965
    Prev
    Next
    INDEX
    Explanations

    client’s publication record

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

    ready to help

    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
    chapters
    0.50
    Chapters
    0.47
     чем
    0.46
     CURLOPT
    0.46
     результате
    0.46
    ﺘ
    0.46
    ᱵ
    0.45
    ዠ
    0.45
    结点
    0.44
    以上に
    0.44
    POSITIVE LOGITS
     Scot
    0.49
     terapeut
    0.47
    wpilib
    0.45
     králov
    0.43
     tieto
    0.43
     Grammar
    0.41
     yt
    0.41
     Qualifying
    0.41
     هنا
    0.41
     ხელ
    0.41
    Activations Density 0.000%

    No Known Activations