© 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. 9427
    Prev
    Next
    INDEX
    Explanations

    staying the course or home

    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
     desapar
    -1.63
    ić
    -1.60
    ać
    -1.58
     eivät
    -1.58
    oucí
    -1.55
    endis
    -1.55
    laient
    -1.52
     και
    -1.52
    粼
    -1.50
    犽
    -1.50
    POSITIVE LOGITS
    i
    1.69
     flesta
    1.62
    ,”
    1.59
     trotz
    1.51
     оценка
    1.48
    ’’
    1.45
    at
    1.42
    긴
    1.42
    anes
    1.41
     ‘’
    1.41
    Activations Density 0.011%

    No Known Activations