© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113850
    Prev
    Next
    INDEX
    Explanations

    act out

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

    The neuron activates on occurrences of the verb “act” (especially “act out”) and its morphological variants (acted, enacting, enact).

    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
    跸
    -1.69
     to
    -1.58
    нием
    -1.57
    \
    -1.56
     Siehe
    -1.56
    ieuse
    -1.52
    氿
    -1.51
     THEOREM
    -1.49
    вге
    -1.48
     \
    -1.47
    POSITIVE LOGITS
     swoich
    1.90
    コマンド
    1.84
    饜
    1.68
    数値
    1.67
     beslut
    1.63
    笮
    1.63
    褙
    1.62
     belangrijk
    1.61
    賡
    1.61
    erintah
    1.60
    Activations Density 0.003%

    No Known Activations