© 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-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 6132
    Prev
    Next
    INDEX
    Explanations

    example usage

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

    The main thing this neuron does is detect mentions of “experience” (and its variants like experienced, Experience) in a professional or résumé context.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    1.60
    at
    1.55
    ت
    1.50
    ন
    1.48
    ol
    1.37
    ro
    1.36
    ul
    1.33
    ために
    1.30
    on
    1.25
    с
    1.21
    POSITIVE LOGITS
     experiencias
    1.45
    IamPermissions
    1.43
     PBMCs
    1.41
    जन्य
    1.41
    娀
    1.34
     WENO
    1.34
    Experiences
    1.33
     Elaina
    1.32
    orrh
    1.31
     Estrella
    1.31
    Activations Density 0.061%

    No Known Activations