© 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. 79079
    Prev
    Next
    INDEX
    Explanations

    square area

    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
     surface
    -4.13
    surface
    -3.52
     Surface
    -3.42
    Surface
    -3.31
     SURFACE
    -2.88
    SURFACE
    -2.73
     surfaces
    -2.61
     superficie
    -2.50
     поверхности
    -2.30
    urface
    -2.23
    POSITIVE LOGITS
    Areas
    0.81
    areas
    0.81
     Areas
    0.77
    ᐝ
    0.76
    Semester
    0.73
    ⛰
    0.71
    rencies
    0.71
     arah
    0.71
    쏴
    0.70
    basketball
    0.69
    Activations Density 0.019%

    No Known Activations