© 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. 2580
    Prev
    Next
    INDEX
    Explanations

    cylindrical shapes

    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
    ̢
    -0.83
    แผ
    -0.82
    ̡
    -0.79
     плит
    -0.78
     PANEL
    -0.76
     CURIAM
    -0.75
    wę
    -0.74
    ҉
    -0.73
    altet
    -0.73
     рам
    -0.71
    POSITIVE LOGITS
     cylindrical
    2.84
     cylinder
    2.66
     cylinders
    2.31
     tube
    2.27
    cylinder
    2.14
     цилинд
    2.02
     Cyl
    2.00
    cyl
    1.98
     Cylinder
    1.98
    Cyl
    1.95
    Activations Density 0.225%

    No Known Activations