© 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. 59048
    Prev
    Next
    INDEX
    Explanations

    number 2 or II

    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
     from
    -2.38
     perpetually
    -2.17
     unrelenting
    -2.11
     unusually
    -2.02
     prevents
    -2.02
     Though
    -1.99
     furthering
    -1.98
     continual
    -1.96
     longstanding
    -1.94
     oddly
    -1.92
    POSITIVE LOGITS
    commonly
    1.87
    苼
    1.80
     astonishing
    1.78
    鹚
    1.72
     constater
    1.71
     amazingly
    1.70
    桫
    1.68
     magnificent
    1.66
    菒
    1.66
    mainly
    1.65
    Activations Density 0.119%

    No Known Activations