© 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. 55846
    Prev
    Next
    INDEX
    Explanations

    text, code, headings

    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
     RUB
    -0.87
    RUB
    -0.84
     QH
    -0.79
    ":"+
    -0.78
    rub
    -0.78
     ADVIS
    -0.77
     Vorschriften
    -0.77
     rub
    -0.75
     Mok
    -0.73
     alté
    -0.71
    POSITIVE LOGITS
     font
    1.17
     text
    1.16
    text
    1.08
     dominant
    1.02
     getText
    0.99
     texto
    0.98
     setText
    0.94
    dx
    0.93
     schreiben
    0.93
    dominant
    0.93
    Activations Density 0.007%

    No Known Activations