© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25079
    Prev
    Next
    INDEX
    Explanations

    stop or low heat

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

    The neuron fires on content‐bearing action words—especially verbs that describe doing or undoing something (e.g. remove, transfer, stop, turn off).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    dives
    -1.11
     trebuie
    -0.97
    āju
    -0.95
    WEAK
    -0.91
    inges
    -0.90
    mentions
    -0.86
    ğından
    -0.84
    tiba
    -0.84
     ウェア
    -0.82
    Actividad
    -0.82
    POSITIVE LOGITS
     and
    1.13
     It
    0.87
    相關
    0.86
    Lying
    0.84
    に行きました
    0.84
     stopped
    0.83
     stopping
    0.82
     descansar
    0.80
     ceased
    0.79
    niająca
    0.78
    Activations Density 0.028%

    No Known Activations