© 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. 76472
    Prev
    Next
    INDEX
    Explanations

    numerical expressions in parentheses

    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
     reduces
    -0.87
    千萬
    -0.85
     ten
    -0.79
    Thirty
    -0.79
     eight
    -0.76
    アジア
    -0.75
    Reduce
    -0.75
    vč
    -0.74
     reducing
    -0.73
    andar
    -0.73
    POSITIVE LOGITS
    三百
    1.24
    二百
    1.23
    ause
    0.88
    fahrzeuge
    0.86
    owicz
    0.85
    atge
    0.83
     véhicule
    0.81
     versão
    0.78
    Leif
    0.77
    щению
    0.77
    Activations Density 0.103%

    No Known Activations