© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34782
    Prev
    Next
    INDEX
    Explanations

    program assertions and conditions

    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
     Checked
    -0.89
    可能是
    -0.74
     preghi
    -0.73
    æd
    -0.72
    XCTAssertEqual
    -0.71
     riguarda
    -0.71
     nincs
    -0.70
    quí
    -0.70
     layanan
    -0.69
     Geburt
    -0.69
    POSITIVE LOGITS
    Contracts
    0.90
     contracts
    0.84
     Conditions
    0.82
    contracts
    0.82
     REQU
    0.77
     condition
    0.76
     precondition
    0.76
    Invariant
    0.75
    ехали
    0.75
     conditions
    0.74
    Activations Density 0.021%

    No Known Activations