© 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. 71351
    Prev
    Next
    INDEX
    Explanations

    official professional titles

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

    The neuron detects mentions of official job titles or administrative positions (e.g. “City Manager,” “County Administrator,” “Township Clerk/Administrator,” etc.).

    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
     tilby
    -1.72
    💮
    -1.63
     动物
    -1.60
     Secretario
    -1.58
    ropractor
    -1.55
     necessariamente
    -1.55
     damski
    -1.53
    っぱり
    -1.53
     帅气
    -1.53
     zů
    -1.52
    POSITIVE LOGITS
    1
    1.96
        
    1.92
    ).
    1.88
    </h3>
    1.75
     -
    1.70
    }\
    1.70
     Only
    1.59
    ip
    1.57
    U
    1.56
    et
    1.54
    Activations Density 0.017%

    No Known Activations