© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66075
    Prev
    Next
    INDEX
    Explanations

    not insignificant, not a little, not least

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

    This neuron detects hedging or emphatic understatement phrases that use negation (e.g. “not insignificant,” “not a little confused,” “more than a little bit”).

    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
     liefern
    -1.51
     przede
    -1.47
     from
    -1.40
     we
    -1.37
    c
    -1.29
    蓠
    -1.29
     głównie
    -1.25
    那我
    -1.25
    mex
    -1.24
    ïque
    -1.23
    POSITIVE LOGITS
     fotográfica
    1.44
     also
    1.41
    bluza
    1.38
     Serviço
    1.31
    fällig
    1.30
    這裡
    1.30
    dö
    1.29
     decorativas
    1.28
     ath
    1.27
    彞
    1.27
    Activations Density 0.029%

    No Known Activations