© 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. 108175
    Prev
    Next
    INDEX
    Explanations

    registration and classification

    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
    jwa
    -0.72
    ligan
    -0.71
     indispens
    -0.71
     victor
    -0.69
    ♝
    -0.68
     snare
    -0.68
    jme
    -0.67
     bitcoins
    -0.66
     récupération
    -0.65
     UPSC
    -0.65
    POSITIVE LOGITS
     Register
    0.93
     rules
    0.90
     registry
    0.87
     thickness
    0.86
     register
    0.86
     class
    0.85
     Rules
    0.84
     design
    0.83
     flags
    0.82
     classification
    0.82
    Activations Density 0.007%

    No Known Activations