© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93307
    Prev
    Next
    INDEX
    Explanations

    `Q:`, `based`, `No`, `/*`, `Co`, `pp`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    тьми
    -0.73
    จัก
    -0.71
    ++)
    -0.70
     incense
    -0.69
     torch
    -0.67
    izh
    -0.65
    跄
    -0.65
    prozess
    -0.65
    pap
    -0.64
    입
    -0.64
    POSITIVE LOGITS
     Wid
    0.69
    urrent
    0.67
    ฐาน
    0.66
    ﾟ)
    0.65
     NDEBUG
    0.63
     Kategorie
    0.63
    ėd
    0.62
     smaller
    0.62
    窪
    0.60
     מרו
    0.60
    Activations Density 0.048%

    No Known Activations