© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25914
    Prev
    Next
    INDEX
    Explanations

    surfaces and substrates

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

    art and scientific materials including papers, canvases, membranes, panels, and other substrate surfaces.

    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_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
    B
    -1.14
     all
    -1.05
    product
    -1.03
     in
    -1.02
    D
    -0.95
    瞞
    -0.94
    🤡
    -0.94
    U
    -0.94
    if
    -0.92
    _
    -0.92
    POSITIVE LOGITS
     waarop
    1.46
    ਖ਼
    1.20
     projekty
    1.20
     راحتی
    1.20
    jestel
    1.14
    jähriger
    1.13
     къде
    1.10
     ($("#
    1.09
    Где
    1.06
    ESSIONAL
    1.05
    Activations Density 0.090%

    No Known Activations