© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 104682
    Prev
    Next
    INDEX
    Explanations

    names after Jack, C, Jack Smith

    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_22/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
     ilumina
    -0.97
    )("
    -0.93
    ....
    -0.93
    ICIÓN
    -0.91
    ).__
    -0.91
     сроки
    -0.89
    ........
    -0.89
    Boston
    -0.87
     or
    -0.86
    ......
    -0.85
    POSITIVE LOGITS
     diverging
    1.23
     paradigms
    1.13
     brooks
    1.09
     formules
    1.09
     Supplements
    1.08
     medley
    1.07
     ―――
    1.06
     passend
    1.05
     delimited
    1.04
     wille
    1.02
    Activations Density 0.182%

    No Known Activations