© 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. 108470
    Prev
    Next
    INDEX
    Explanations

    boolean true false evaluation

    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
     замет
    -0.84
     có
    -0.82
     bukanlah
    -0.73
    assertNot
    -0.71
    XCTAssertEqual
    -0.71
     album
    -0.70
    Mand
    -0.70
    UINT
    -0.68
    plotlib
    -0.68
    IOException
    -0.68
    POSITIVE LOGITS
     false
    0.97
    stdbool
    0.93
    偽
    0.92
     falsehood
    0.88
     truth
    0.86
    assertFalse
    0.85
     False
    0.85
     fake
    0.82
    possibly
    0.82
    evaluation
    0.81
    Activations Density 0.027%

    No Known Activations