© 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. 10-GEMMASCOPE-RES-131K
    7. 71389
    Prev
    Next
    INDEX
    Explanations

    reversibility and mucosa

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

    This neuron detects technical or academic terms, particularly looking for reversibility and file/programming terminology.

    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
    s
    -4.09
    y
    -3.73
    d
    -3.34
    ing
    -3.22
    r
    -2.72
    ).
    -2.55
    ים
    -2.48
    we
    -2.47
    ’，
    -2.45
    主要是
    -2.44
    POSITIVE LOGITS
    ي
    3.66
    妧
    3.11
     been
    2.97
    𓍊
    2.73
    ὂ
    2.67
     Verpflich
    2.53
    ين
    2.53
     οποία
    2.53
    其妙
    2.52
    鲧
    2.52
    Activations Density 0.051%

    No Known Activations