© 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. 73812
    Prev
    Next
    INDEX
    Explanations

    list and array initialization

    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
     unrelenting
    -2.52
     perplexing
    -2.31
     extraordinarily
    -2.19
     fourteen
    -2.11
     perpetually
    -2.09
     troubling
    -2.05
     vehemently
    -2.05
     supremely
    -2.03
     relentlessly
    -2.03
     classy
    -2.03
    POSITIVE LOGITS
     dando
    2.14
     delightfully
    2.13
     decidedly
    2.11
     quintessential
    2.09
     lauded
    2.00
     fabulous
    2.00
     REALLY
    1.98
     deliciously
    1.95
     delectable
    1.95
     wondrous
    1.94
    Activations Density 0.001%

    No Known Activations