© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103977
    Prev
    Next
    INDEX
    Explanations

    in particular

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

    The neuron flags small parenthetical qualifier phrases (e.g. “in particular,” “if applicable,” “in part,” etc.) that introduce an aside or elaboration.

    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
     vitales
    -1.50
    in
    -1.50
    li
    -1.48
    u
    -1.45
    }\
    -1.45
     arba
    -1.42
    h
    -1.40
    حتی
    -1.30
     &
    -1.29
    four
    -1.28
    POSITIVE LOGITS
     Waktu
    1.50
     Lainnya
    1.45
     September
    1.44
     Перейти
    1.41
    cuencia
    1.40
    vább
    1.38
    madeus
    1.36
    íble
    1.35
     individuo
    1.35
    ◆◇
    1.34
    Activations Density 0.041%

    No Known Activations