© 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. 65200
    Prev
    Next
    INDEX
    Explanations

    Java code fragments

    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
     even
    -0.99
     religiosas
    -0.89
     harness
    -0.88
     incur
    -0.87
    ſi
    -0.85
    ابة
    -0.84
     годи
    -0.84
     NYC
    -0.82
     getNome
    -0.81
    CCIÓN
    -0.81
    POSITIVE LOGITS
    Integer
    1.08
     BigDecimal
    1.03
    Long
    1.03
    String
    1.00
     Integer
    1.00
     JACKSON
    0.94
    LOGGER
    0.93
    itoa
    0.92
    avadoc
    0.91
     prospet
    0.90
    Activations Density 0.002%

    No Known Activations