© 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. 10-GEMMASCOPE-RES-131K
    7. 13666
    Prev
    Next
    INDEX
    Explanations

    negation followed by common words

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

    The neuron flags the main finite verbs and auxiliaries that carry the clause predicate (e.g. “keeps,” “is,” “makes,” “not”).

    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
     this
    -1.65
     sparkly
    -1.63
     or
    -1.56
    <td>
    -1.55
     before
    -1.55
     took
    -1.53
    tedrale
    -1.52
     belligerent
    -1.48
     gets
    -1.48
     gave
    -1.48
    POSITIVE LOGITS
     remarkably
    1.70
    rfan
    1.67
     broader
    1.67
    aning
    1.63
     bedeutend
    1.59
    が少ない
    1.55
    ruka
    1.55
    į
    1.54
     crucial
    1.52
     Р
    1.52
    Activations Density 0.012%

    No Known Activations