© 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. 99763
    Prev
    Next
    INDEX
    Explanations

    not much, not many, not adequate

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

    This neuron specializes in spotting the negation “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
    塒
    -2.02
    糴
    -1.90
    最初の
    -1.88
     Gebruik
    -1.85
     estadounid
    -1.83
     bocetos
    -1.80
     tappa
    -1.77
    </i>
    -1.77
     diametro
    -1.77
     sewa
    -1.77
    POSITIVE LOGITS
     
    2.16
    <bos>
    2.02
    </strong>
    1.88
     ;
    1.83
     a
    1.82
    ?
    1.75
    色は
    1.71
     )
    1.70
    ),
    1.68
     *
    1.63
    Activations Density 0.007%

    No Known Activations