© 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. 81601
    Prev
    Next
    INDEX
    Explanations

    players

    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
    日から
    -0.92
     might
    -0.86
     gives
    -0.84
    //"
    -0.81
     or
    -0.81
     allows
    -0.80
     increased
    -0.79
     provides
    -0.79
    //'
    -0.78
     garner
    -0.77
    POSITIVE LOGITS
    ¹,
    0.97
     przeciw
    0.93
    nste
    0.88
     unn
    0.87
     bohater
    0.85
     instruções
    0.85
    LayoutParams
    0.84
    NER
    0.84
    thylamine
    0.83
     gdy
    0.83
    Activations Density 0.001%

    No Known Activations