© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118847
    Prev
    Next
    INDEX
    Explanations

    paper references and symbols

    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
    {"{
    -0.79
     阅读
    -0.76
    תר
    -0.74
     Spielen
    -0.72
    衫
    -0.72
    ighters
    -0.71
    rupp
    -0.69
     olvido
    -0.69
    Atención
    -0.69
     sostu
    -0.69
    POSITIVE LOGITS
     Teste
    0.77
    това
    0.74
    回
    0.68
     Troubles
    0.68
    chläge
    0.67
     Incidents
    0.67
     Cataluña
    0.66
     DUE
    0.66
     burlesque
    0.66
     символ
    0.66
    Activations Density 0.031%

    No Known Activations