© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110726
    Prev
    Next
    INDEX
    Explanations

    Flying Triangle

    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
    PutPixel
    -0.72
    loadMore
    -0.68
     Himmels
    -0.68
     cin
    -0.67
    iber
    -0.66
     jitter
    -0.66
     flicker
    -0.65
    ケル
    -0.65
    INDU
    -0.65
    Induction
    -0.65
    POSITIVE LOGITS
     outside
    1.17
    outside
    1.08
    wares
    1.00
     apron
    0.95
    外
    0.93
    Outside
    0.92
    laz
    0.92
     外
    0.85
     Outside
    0.83
     dış
    0.81
    Activations Density 0.010%

    No Known Activations