© 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. 48820
    Prev
    Next
    INDEX
    Explanations

    peace activist

    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
     Muhammad
    -0.84
    慕
    -0.80
     Mohammad
    -0.75
     Gew
    -0.74
    epsfig
    -0.73
     zwei
    -0.73
     intuitive
    -0.72
     Michael
    -0.72
     artist
    -0.71
     an
    -0.71
    POSITIVE LOGITS
    exports
    0.88
     lumens
    0.84
    
    0.83
    BERRY
    0.83
    upon
    0.80
     gekennzeichnet
    0.80
    
    0.78
    hereinafter
    0.76
     déterminé
    0.76
    度は
    0.76
    Activations Density 0.016%

    No Known Activations