© 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. 10-GEMMASCOPE-RES-131K
    4. 101884
    Prev
    Next
    INDEX
    Explanations

    rejection and rejected

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

    The main thing this neuron does is detect occurrences of the root “reject” (e.g. reject, rejection, rejecting) or closely related disapproval terms.

    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
    .”
    -1.80
    </em>
    -1.71
    睺
    -1.67
     interesan
    -1.62
     heuti
    -1.62
     proporcionan
    -1.59
    któ
    -1.52
     harán
    -1.52
    
    -1.50
     včetně
    -1.49
    POSITIVE LOGITS
     with
    2.34
    ="
    1.91
    是個
    1.79
     from
    1.78
    描く
    1.73
     of
    1.68
     voyez
    1.64
     for
    1.63
    >
    1.63
     part
    1.60
    Activations Density 0.007%

    No Known Activations