© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99476
    Prev
    Next
    INDEX
    Explanations

    geographic and celestial poles

    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
    ෑ
    -0.79
    trät
    -0.75
    ungkin
    -0.72
    ganu
    -0.71
    льне
    -0.69
     Kies
    -0.69
     wizards
    -0.68
    ärin
    -0.68
     مسئول
    -0.68
    вали
    -0.68
    POSITIVE LOGITS
     poles
    3.53
     pole
    3.45
     Pole
    2.92
     polar
    2.78
    pole
    2.70
    Pole
    2.69
     Poles
    2.67
    poles
    2.39
    polar
    2.38
     Polar
    2.30
    Activations Density 0.037%

    No Known Activations