© 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. 106650
    Prev
    Next
    INDEX
    Explanations

    mathematical infinities and limits

    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
    ECONDS
    -0.71
    🕎
    -0.69
     Erle
    -0.68
     froh
    -0.68
     wey
    -0.67
     SNOW
    -0.66
    XCTAssertEqual
    -0.66
     Addams
    -0.65
     装修
    -0.65
    AGUA
    -0.65
    POSITIVE LOGITS
     infinity
    4.47
    infinity
    3.64
    infty
    3.63
     Infinity
    3.55
    Infinity
    3.34
     ∞
    3.08
    ∞
    3.00
     infinite
    2.98
     infinito
    2.92
     INFIN
    2.77
    Activations Density 0.069%

    No Known Activations