© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27517
    Prev
    Next
    INDEX
    Explanations

    canceled, abandoned, scrapped, ended

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

    This neuron detects contrastive or negation cues—function words and verbs signaling reversal, cancellation, or “but/not”–style shifts in a sentence.

    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
     a
    -1.28
    本当は
    -1.13
    formerly
    -1.05
    Shouldn
    -0.98
    Already
    -0.97
    僕も
    -0.96
    Trying
    -0.95
     triko
    -0.94
    previously
    -0.93
    中略
    -0.92
    POSITIVE LOGITS
     because
    1.48
     it
    1.36
    เพราะ
    1.30
    だったので
    1.21
     ended
    1.17
    ʷ
    1.12
    結局
    1.10
     due
    1.09
     ultimately
    1.05
     नहीं
    1.05
    Activations Density 0.038%

    No Known Activations