© 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. 10-GEMMASCOPE-RES-131K
    4. 12017
    Prev
    Next
    INDEX
    Explanations

    available data, evidence, resources

    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_10/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
     Polícia
    -1.80
     they
    -1.78
    ridescent
    -1.77
     atriz
    -1.76
    ELTS
    -1.73
    👊
    -1.70
    eeeeee
    -1.69
    RRRR
    -1.66
     cantora
    -1.65
    peo
    -1.63
    POSITIVE LOGITS
    ࿚
    2.02
     wildly
    1.84
     newly
    1.74
     fierce
    1.73
     seemingly
    1.70
     recently
    1.69
     powerful
    1.68
     Recently
    1.67
     brilliantly
    1.63
     sprawling
    1.63
    Activations Density 0.013%

    No Known Activations