© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110804
    Prev
    Next
    INDEX
    Explanations

    to the fullest

    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
     alkoh
    -0.88
     期
    -0.86
     logis
    -0.83
     friv
    -0.82
    amerika
    -0.80
     Amerika
    -0.79
     talle
    -0.79
     Illinois
    -0.78
     Specs
    -0.76
     sida
    -0.75
    POSITIVE LOGITS
     fullest
    0.85
     вдоль
    0.83
    Nguyen
    0.81
    roblast
    0.80
    Racer
    0.77
    漓
    0.76
    扬
    0.76
     hilt
    0.75
     marrow
    0.73
     hueso
    0.73
    Activations Density 0.014%

    No Known Activations