© 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. 107897
    Prev
    Next
    INDEX
    Explanations

    code delimiters or identifiers

    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
    Bernard
    -0.75
    
    -0.72
    🏋
    -0.70
     capabilities
    -0.70
    processData
    -0.69
    య
    -0.69
    NOWLED
    -0.69
    Lou
    -0.69
    ztat
    -0.68
     amerik
    -0.68
    POSITIVE LOGITS
     Trus
    0.88
     aspiring
    0.83
     ablation
    0.83
     sentirse
    0.81
    omitempty
    0.79
     Nordstrom
    0.79
     Botschaft
    0.78
     spezif
    0.78
     anten
    0.78
    さっき
    0.77
    Activations Density 0.002%

    No Known Activations