© 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. 22-GEMMASCOPE-RES-131K
    7. 73398
    Prev
    Next
    INDEX
    Explanations

    knew it was

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

    The neuron detects cognitive or perceptual verbs—especially forms of “know” (e.g. “knew”) and similar sensing or thinking words like “sounded” and “wondering.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Currently
    -1.08
    と思っている
    -1.06
     currently
    -1.05
    Currently
    -1.03
    currently
    -0.99
     recherchez
    -0.99
    Výhody
    -0.96
     soziale
    -0.93
    Сейчас
    -0.91
     stessa
    -0.89
    POSITIVE LOGITS
     wasn
    1.33
     something
    1.20
     was
    1.15
    '
    1.13
     mutta
    1.13
    Choisissez
    1.05
     comenzó
    1.03
     didn
    1.01
    子さん
    1.01
     però
    1.00
    Activations Density 0.017%

    No Known Activations