© 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. 9023
    Prev
    Next
    INDEX
    Explanations

    random.randint, vacant properties, OA

    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
    
    -3.11
    🧌
    -3.11
     装着
    -3.06
     enthou
    -2.91
     fidé
    -2.89
    
    -2.86
    翃
    -2.78
    乀
    -2.73
    ſche
    -2.72
     lamenta
    -2.69
    POSITIVE LOGITS
    –
    3.28
    i
    3.23
    a
    3.23
    -
    3.22
    3
    3.19
    <i>
    3.03
    0
    3.02
    il
    3.00
     $
    2.97
    e
    2.95
    Activations Density 0.003%

    No Known Activations