© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14629
    Prev
    Next
    INDEX
    Explanations

    html table cells or quoted strings

    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
     عندما
    -1.73
    ་་
    -1.66
     сказала
    -1.63
    Does
    -1.62
    Different
    -1.61
     umani
    -1.59
     如果
    -1.55
    ？』
    -1.55
    mohon
    -1.55
     будет
    -1.55
    POSITIVE LOGITS
    {\
    2.28
     \
    1.81
    itzende
    1.65
    ogues
    1.59
    icoot
    1.58
    mindedness
    1.55
     counteract
    1.52
     of
    1.52
     \"
    1.51
    鼙
    1.51
    Activations Density 0.006%

    No Known Activations