© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99306
    Prev
    Next
    INDEX
    Explanations

    Cato, Voltaire, Clay, Vernon

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

    The neuron activates on capitalized proper names—especially personal surnames.

    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
     öde
    -1.66
     =>
    -1.52
     amac
    -1.45
     логоти
    -1.43
    
    -1.40
     avantage
    -1.38
    ſche
    -1.38
     you
    -1.37
     ()
    -1.36
    cisive
    -1.34
    POSITIVE LOGITS
    ↵↵
    1.77
    ↵
    1.45
    </em>
    1.44
     struggles
    1.38
    </h3>
    1.37
     misteriosa
    1.32
     einzigen
    1.32
     älteren
    1.30
     endast
    1.29
     was
    1.25
    Activations Density 0.018%

    No Known Activations