© 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. 10-GEMMASCOPE-RES-131K
    7. 385
    Prev
    Next
    INDEX
    Explanations

    cited results

    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
     the
    -1.96
     also
    -1.88
     a
    -1.80
     نیز
    -1.75
    ,’
    -1.59
     木製
    -1.58
     cristian
    -1.58
    場は
    -1.52
    !’
    -1.50
    2
    -1.49
    POSITIVE LOGITS
     asegurarse
    1.67
    .
    1.63
     that
    1.63
     particularmente
    1.59
    参见
    1.57
    ？！”
    1.56
    {}
    1.55
     mantenerse
    1.54
    恸
    1.51
     škole
    1.49
    Activations Density 0.002%

    No Known Activations