© 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. 111609
    Prev
    Next
    INDEX
    Explanations

    architecture

    np_acts-logits-general · gemini-2.5-flash-lite

    the word "architecture" in technical and formal contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    鲧
    -2.48
    joyed
    -2.30
    ꯶
    -2.22
    
    -2.13
     美甲
    -2.08
    
    -2.02
     unſ
    -1.98
    actie
    -1.95
    struzione
    -1.91
    ྥ
    -1.88
    POSITIVE LOGITS
    (
    2.27
    その他
    1.86
    贩
    1.84
     beiden
    1.76
    \
    1.70
    U
    1.70
    </sup>
    1.67
     &
    1.66
    in
    1.64
    多种
    1.59
    Activations Density 0.014%

    No Known Activations