© 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. 29194
    Prev
    Next
    INDEX
    Explanations

    not, no, never, cannot

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

    The neuron fires on negation words and negative qualifiers (e.g. no, not, never, n't, nowhere, only in a restricting sense).

    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
     بدون
    -1.38
    isés
    -1.30
     akár
    -1.21
     )}$
    -1.13
    MIN
    -1.11
    mités
    -1.09
    ões
    -1.09
    picable
    -1.07
    GL
    -1.05
     даже
    -1.05
    POSITIVE LOGITS
    近くに
    1.18
     azúcar
    1.12
    máscara
    1.10
     two
    1.09
    camisa
    1.07
     wiederum
    1.06
    arriver
    1.06
     about
    1.06
    ווע
    1.05
     Asegúrese
    1.05
    Activations Density 0.090%

    No Known Activations