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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10611
    Prev
    Next
    INDEX
    Explanations

    et al

    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_10/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
    <i>
    -3.61
    on
    -2.67
    m
    -2.66
    ro
    -2.64
    8
    -2.53
    0
    -2.50
    1
    -2.41
    i
    -2.31
    g
    -2.27
    3
    -2.27
    POSITIVE LOGITS
     lamenta
    2.78
    🫓
    2.50
     participó
    2.47
     revelado
    2.42
    </em>
    2.39
     abandonado
    2.36
    蹰
    2.30
     sufrió
    2.23
    
    2.23
    ')):
    2.22
    Activations Density 0.001%

    No Known Activations