© 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. 30841
    Prev
    Next
    INDEX
    Explanations

    compilation unit file scope

    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
    cityName
    -0.69
    sara
    -0.67
    FIRE
    -0.67
     vivió
    -0.66
    MES
    -0.66
     poêle
    -0.65
     REFERENCES
    -0.65
    ột
    -0.64
    hau
    -0.62
    Etiquetas
    -0.62
    POSITIVE LOGITS
     compilation
    1.59
     translation
    1.47
     Translation
    1.38
     Compilation
    1.36
     unit
    1.32
    compilation
    1.31
    Compilation
    1.30
     units
    1.30
    Translation
    1.29
     file
    1.22
    Activations Density 0.117%

    No Known Activations