© 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. 22-GEMMASCOPE-RES-131K
    7. 26401
    Prev
    Next
    INDEX
    Explanations

    Chief Executive Officer, Dean, Registrar

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

    This neuron detects mentions of holding or serving in official roles (job titles, positions, and related appointment phrases).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    🪬
    -1.13
     criptomonedas
    -1.06
    】:
    -1.06
     today
    -1.05
     magasiner
    -1.03
     geene
    -1.02
     pauv
    -1.00
    aarr
    -0.98
     tonight
    -0.96
     pratiquer
    -0.96
    POSITIVE LOGITS
     as
    1.19
     As
    1.05
     Lead
    1.04
     in
    1.04
    Then
    1.01
    ơ
    1.00
    渣
    0.99
     Thus
    0.98
    ológicos
    0.96
     ski
    0.95
    Activations Density 0.064%

    No Known Activations