© 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. 84191
    Prev
    Next
    INDEX
    Explanations

    Latter-Day Saints; chemical formulas

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

    subscript notation in mathematical and scientific formulas, especially numerical subscripts in chemical formulas.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on LaTeX/math‐mode control sequences (e.g. “\underset”) and related math‐formatting tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    -2.47
    5
    -2.34
    a
    -2.34
    4
    -2.25
    Not
    -2.19
    那我
    -2.16
    ch
    -2.13
    To
    -2.05
    end
    -1.99
    3
    -1.98
    POSITIVE LOGITS
    และ
    2.42
     But
    2.39
    儅
    2.34
     situés
    2.25
     lección
    2.19
     Для
    2.16
     sabias
    2.13
     }_{
    2.09
     selben
    2.09
     Также
    2.05
    Activations Density 0.001%

    No Known Activations