© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 405
    Prev
    Next
    INDEX
    Explanations

    not letting deter stop

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

    This neuron detects strong “not/never” constructions with verbs like let, make, sideline, or scare—phrases expressing refusal or resistance (e.g. “not letting cancer sideline him,” “isn’t scaring me away,” “nothing could make you…,” “won’t let one individual…”).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    鹜
    -0.87
     tén
    -0.78
    erecht
    -0.77
    zó
    -0.77
     teléfono
    -0.75
     фун
    -0.75
     ہے۔
    -0.75
    <0x96>
    -0.74
    ALING
    -0.73
     пло
    -0.73
    POSITIVE LOGITS
     deter
    1.40
     affect
    1.27
     dissu
    1.26
     deterred
    1.18
     stop
    1.18
     stopping
    1.11
    وقف
    1.08
     AFFECT
    1.07
     affecting
    1.02
    阻止
    1.02
    Activations Density 0.019%

    No Known Activations