© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 75836
    Prev
    Next
    INDEX
    Explanations

    copyright holders

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

    This neuron responds to sequences of digits or extended hyphen‐dash lines (e.g. long rows of “—” or standalone numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ItemType
    -0.70
    away
    -0.67
    ாய
    -0.66
    REPLACE
    -0.65
    hages
    -0.65
     Huh
    -0.64
     ItemType
    -0.64
    नलिखित
    -0.63
    cista
    -0.62
    FILTER
    -0.61
    POSITIVE LOGITS
     Depot
    0.65
     Sonny
    0.64
    DMS
    0.63
     impartial
    0.62
    ToAction
    0.62
    sommer
    0.62
    Addon
    0.61
    Curr
    0.61
    gui
    0.61
    тери
    0.60
    Activations Density 0.090%

    No Known Activations