© 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. 71179
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
    ínica
    -0.94
     précisé
    -0.87
    weta
    -0.81
     burch
    -0.81
    clover
    -0.81
     实现
    -0.81
    為に
    -0.79
     metų
    -0.79
     also
    -0.78
     може
    -0.77
    POSITIVE LOGITS
    aving
    0.96
    lings
    0.95
    ration
    0.95
     autre
    0.90
    Therefore
    0.90
    tains
    0.88
    other
    0.88
    tings
    0.87
    tivity
    0.87
    ensões
    0.85
    Activations Density 0.002%

    No Known Activations