© 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. 34-GEMMASCOPE-RES-131K
    7. 107434
    Prev
    Next
    INDEX
    Explanations

    opening up about or opened about

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

    The neuron selectively fires on verbs in their participle or gerund forms—that is, words ending in “-ed” or “-ing.”

    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
    臬
    -0.72
    ideae
    -0.68
    medida
    -0.66
     over
    -0.66
     precursor
    -0.65
    towanie
    -0.65
    joueurs
    -0.63
    зоры
    -0.63
     precursors
    -0.62
    PDT
    -0.62
    POSITIVE LOGITS
    leggen
    0.73
    ELS
    0.68
     художе
    0.67
    etten
    0.65
    OGEN
    0.65
    トレ
    0.63
     postnatal
    0.63
    arte
    0.60
    ISSION
    0.60
    yski
    0.60
    Activations Density 0.070%

    No Known Activations