© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12707
    Prev
    Next
    INDEX
    Explanations

    conjunctions and lists

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

    The neuron strongly activates on negation or prohibition cues (e.g. “forget,” “never”). It flags words expressing a negative or forbidding 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_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
     of
    -1.55
    ఽ
    -1.34
     infrar
    -1.27
    SFER
    -1.26
     oliveira
    -1.24
     alis
    -1.21
     rigide
    -1.19
     sedi
    -1.18
     sirop
    -1.17
     munici
    -1.16
    POSITIVE LOGITS
     and
    2.64
     or
    2.25
     new
    1.30
     или
    1.22
     puntas
    1.20
     three
    1.14
     alebo
    1.14
     hambre
    1.13
     abundancia
    1.10
     apreciar
    1.09
    Activations Density 0.042%

    No Known Activations