© 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. 109359
    Prev
    Next
    INDEX
    Explanations

    early in or on

    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
     asalto
    -1.09
     nutrición
    -1.03
     excelencia
    -1.01
     tejidos
    -0.96
     asientos
    -0.95
    עיף
    -0.93
     chua
    -0.92
    bewah
    -0.91
    多年
    -0.91
     urgencia
    -0.91
    POSITIVE LOGITS
     in
    2.63
     on
    1.23
     into
    1.18
     When
    1.01
     when
    1.01
    <0xA3>
    0.99
     During
    0.98
    When
    0.94
    тельный
    0.93
     during
    0.93
    Activations Density 0.022%

    No Known Activations