© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86233
    Prev
    Next
    INDEX
    Explanations

    specific substances and actions

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

    The neuron fires on mentions of riot‐control or nonlethal crowd-control weapons (e.g. tear gas, pepper spray, flash bombs).

    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
     this
    -1.79
     that
    -1.57
     some
    -1.26
     problemen
    -1.24
    (
    -1.23
     decorativos
    -1.20
    谘
    -1.17
     твоя
    -1.16
    飒
    -1.16
    L
    -1.16
    POSITIVE LOGITS
    Their
    1.34
     jejich
    1.30
    uegos
    1.29
     їх
    1.28
    (",",
    1.23
    ཽ
    1.23
     begge
    1.20
     их
    1.20
     telefonu
    1.19
    animity
    1.17
    Activations Density 0.019%

    No Known Activations