© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71068
    Prev
    Next
    INDEX
    Explanations

    introduces lists of details or options

    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_22/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
     none
    -0.95
     only
    -0.91
     saw
    -0.90
     gerekir
    -0.89
     yoktur
    -0.88
    thail
    -0.87
    gilet
    -0.85
    ufes
    -0.84
     εί
    -0.84
     مربوط
    -0.82
    POSITIVE LOGITS
     you
    1.36
    поги
    1.01
    ёг
    1.01
    umab
    0.98
    ándote
    0.96
    доль
    0.95
     GeoNames
    0.94
    Highlights
    0.94
    lež
    0.93
    któ
    0.93
    Activations Density 0.058%

    No Known Activations