© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90324
    Prev
    Next
    INDEX
    Explanations

    fine art

    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
    ysis
    -0.85
    romyal
    -0.85
    طة
    -0.84
     refleja
    -0.82
    imiento
    -0.81
    和我
    -0.79
     («
    -0.79
    顔が
    -0.79
     schein
    -0.79
     kroner
    -0.78
    POSITIVE LOGITS
    fine
    1.86
     tuned
    1.81
     fine
    1.79
     tuning
    1.78
     Fine
    1.76
     FINE
    1.72
    Fine
    1.72
    tuning
    1.61
     grained
    1.55
     Tuning
    1.52
    Activations Density 0.017%

    No Known Activations