© 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. 86602
    Prev
    Next
    INDEX
    Explanations

    pass rush and game actions

    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
    駸
    -1.67
    〝
    -1.65
    zené
    -1.59
     姉
    -1.59
     papà
    -1.56
     Organiser
    -1.55
     valuing
    -1.52
    摃
    -1.52
     櫃
    -1.51
     Thermometer
    -1.50
    POSITIVE LOGITS
     n
    1.52
    *
    1.48
     "
    1.48
    '"
    1.47
     quieran
    1.45
    en
    1.44
     dejen
    1.42
     _
    1.41
     er
    1.39
    ers
    1.38
    Activations Density 0.004%

    No Known Activations