© 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. 10-GEMMASCOPE-RES-131K
    7. 87300
    Prev
    Next
    INDEX
    Explanations

    structural components, characteristics, and changes

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

    words and phrases related to structural components or properties in technical and scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    厛
    -2.84
    鯪
    -2.61
    xvii
    -2.58
    쫀
    -2.56
    _),
    -2.45
    뿅
    -2.39
    鐃
    -2.39
    怱
    -2.36
    ötzlich
    -2.27
     nasceu
    -2.27
    POSITIVE LOGITS
    V
    3.72
    T
    3.72
    J
    3.67
    H
    3.56
    E
    3.56
    al
    3.39
    re
    3.34
    Q
    3.30
    B
    3.28
    N
    3.23
    Activations Density 0.010%

    No Known Activations