© 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. 115487
    Prev
    Next
    INDEX
    Explanations

    GitHub, repositories, enterprise

    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
    лектро
    -0.85
    doin
    -0.81
    tslib
    -0.77
     기
    -0.77
    ﴾
    -0.76
     antibiotic
    -0.75
     ス
    -0.75
    र्ष
    -0.74
     Estado
    -0.73
    arl
    -0.73
    POSITIVE LOGITS
     enterprise
    0.90
    enterprise
    0.82
     actions
    0.81
     Montevideo
    0.80
     प्रयास
    0.80
    empresa
    0.79
     Actions
    0.79
    左侧
    0.79
     Organis
    0.76
    Реги
    0.76
    Activations Density 0.047%

    No Known Activations