© 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. 22-GEMMASCOPE-RES-131K
    7. 35178
    Prev
    Next
    INDEX
    Explanations

    questions and statements beginning now or with align

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

    The neuron specifically detects LaTeX “align” equation environment markers (i.e. occurrences of the align environment in math mode).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     хвилин
    -1.46
     after
    -1.44
     However
    -1.38
    閬
    -1.37
    ранее
    -1.34
     Архиви
    -1.32
    bilden
    -1.30
     Ayrıca
    -1.29
     These
    -1.29
     already
    -1.29
    POSITIVE LOGITS
    ↵
    1.61
    </em>
    1.40
    ?”
    1.30
    .
    1.29
     hermosos
    1.27
    ),”
    1.26
     hermosas
    1.23
     zeven
    1.21
    h
    1.19
    chaun
    1.18
    Activations Density 0.000%

    No Known Activations