© 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. 58383
    Prev
    Next
    INDEX
    Explanations

    experimental art and media

    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
     sob
    -0.93
     nostal
    -0.91
     pojawi
    -0.90
     HISTORICAL
    -0.90
     оптима
    -0.90
     clich
    -0.88
     rodríguez
    -0.88
    kaper
    -0.86
     космети
    -0.85
     hypocrite
    -0.84
    POSITIVE LOGITS
     experimental
    1.67
     avant
    1.65
    Experimental
    1.47
     weird
    1.45
     surreal
    1.40
    experimental
    1.36
     vanguardia
    1.30
    实验
    1.30
     abstract
    1.29
     Experimental
    1.28
    Activations Density 0.072%

    No Known Activations