© 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. 78087
    Prev
    Next
    INDEX
    Explanations

    Copyright dates, times, and sources

    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
     kaynağından
    -0.89
     augusti
    -0.86
    xffffffff
    -0.85
    cE
    -0.85
     coklat
    -0.85
     fraude
    -0.83
     fantastisk
    -0.80
    xFFFFFF
    -0.78
     Comunicação
    -0.78
    
    -0.78
    POSITIVE LOGITS
     behauptet
    0.85
     navire
    0.81
    Pig
    0.81
     Ostra
    0.78
    Loading
    0.77
    kleidung
    0.75
    enziale
    0.75
     loads
    0.75
    מבר
    0.74
    load
    0.74
    Activations Density 0.001%

    No Known Activations