© 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. 60369
    Prev
    Next
    INDEX
    Explanations

    words starting with cra

    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
    菹
    -3.47
    
    -3.33
    媵
    -3.20
    ܞ
    -3.06
     土産
    -2.95
    栴
    -2.92
    igslist
    -2.92
    晙
    -2.88
    髫
    -2.83
     และ
    -2.78
    POSITIVE LOGITS
    0
    3.38
    <i>
    3.08
    2
    3.02
    begin
    2.88
    a
    2.84
    )
    2.66
    3
    2.58
    出て
    2.55
    2.52
     gets
    2.47
    Activations Density 0.003%

    No Known Activations