© 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. 55624
    Prev
    Next
    INDEX
    Explanations

    web server code

    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
    ishima
    -0.89
    sieke
    -0.87
     Possibly
    -0.85
    ftar
    -0.82
    ӗ
    -0.81
    ')}}">
    -0.81
    asthan
    -0.81
    зывают
    -0.79
    WEBPACK
    -0.77
    paramInt
    -0.76
    POSITIVE LOGITS
     port
    0.93
     apporter
    0.84
    端口
    0.81
     PORT
    0.80
     Port
    0.77
     skier
    0.73
    Port
    0.71
     гриб
    0.71
     Gelen
    0.71
    ให้
    0.70
    Activations Density 0.006%

    No Known Activations