© 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. 10-GEMMASCOPE-RES-131K
    7. 86376
    Prev
    Next
    INDEX
    Explanations

    urusan, bmatrix, incontinence

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

    The neuron is primarily detecting document-structure markers such as section headings, summary separators (e.g. lines of “=”), and LaTeX/math environment 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
    ⧠
    -2.84
     Betracht
    -2.63
    珰
    -2.48
    栒
    -2.47
    臜
    -2.38
     dejando
    -2.36
     leaſt
    -2.28
    -2.27
    瞜
    -2.27
    珖
    -2.23
    POSITIVE LOGITS
    t
    3.19
     With
    3.08
    with
    2.64
    ቾ
    2.42
    COLOG
    2.36
    ❉
    2.36
     avec
    2.33
    ции
    2.33
    ere
    2.31
     όταν
    2.31
    Activations Density 0.015%

    No Known Activations