© 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. 97741
    Prev
    Next
    INDEX
    Explanations

    watch descriptions and specific names

    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
    bett
    -0.84
    Redraw
    -0.82
    leman
    -0.80
    χεία
    -0.80
     magnum
    -0.77
    canakan
    -0.76
     fleuve
    -0.75
     tế
    -0.74
    KeepAlive
    -0.74
    Social
    -0.73
    POSITIVE LOGITS
     bezel
    1.34
     unid
    0.89
     timer
    0.81
     compute
    0.79
     Pepsi
    0.79
    timer
    0.78
     Bezos
    0.74
     дай
    0.74
     bez
    0.73
     rotates
    0.73
    Activations Density 0.016%

    No Known Activations