© 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. 49259
    Prev
    Next
    INDEX
    Explanations

    Q/A structuring, XML binding, specific terms

    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
    だけに
    -0.74
     ciutat
    -0.68
     responded
    -0.68
     cilvē
    -0.67
     all
    -0.67
     each
    -0.66
     spē
    -0.66
     přístup
    -0.66
     والج
    -0.66
     cikin
    -0.66
    POSITIVE LOGITS
    zied
    0.89
     SUBST
    0.89
    "}},
    0.82
    blockSize
    0.81
    ⇌
    0.78
    TextSize
    0.77
    DataType
    0.77
    eable
    0.77
     marshall
    0.77
    mately
    0.76
    Activations Density 0.004%

    No Known Activations