© 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. 103679
    Prev
    Next
    INDEX
    Explanations

    referral or referring

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

    The neuron primarily detects occurrences of the root “refer” (e.g. referred, referral, referrals) in various morphological forms.

    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
    <bos>
    -2.08
    ܆
    -1.81
    ânsito
    -1.75
    𖤍
    -1.74
    ズニー
    -1.74
    .*")]
    -1.73
    翃
    -1.71
    uminense
    -1.70
     «
    -1.70
    身影
    -1.70
    POSITIVE LOGITS
    
    2.03
    还是要
    2.00
     Noviembre
    1.95
     to
    1.77
    ’
    1.70
    </sup>
    1.66
     Our
    1.63
     Instead
    1.60
     estrena
    1.59
     titolata
    1.59
    Activations Density 0.016%

    No Known Activations