© 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. 107079
    Prev
    Next
    INDEX
    Explanations

    lectures and talks

    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
    ReadKey
    -0.83
    setzungen
    -0.74
    นด์
    -0.73
     yetu
    -0.73
    TestResult
    -0.72
    ージェ
    -0.72
     け
    -0.71
    nehå
    -0.70
    liny
    -0.69
     امروز
    -0.69
    POSITIVE LOGITS
     lecture
    4.75
     lectures
    4.72
    lecture
    3.47
     Lecture
    3.47
    Lecture
    3.31
     Lectures
    3.16
     лек
    3.00
    Lectures
    2.78
    lect
    2.73
     lecturer
    2.69
    Activations Density 0.056%

    No Known Activations