© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4512
    Prev
    Next
    INDEX
    Explanations

    difficulty obtaining

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

    The neuron activates on words that introduce or emphasize required skills or qualifications (e.g. Ability, Knowledge, Familiarity, Strong, Professional) in a job description.

    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
    This
    0.70
    Business
    0.69
    Ү
    0.69
    Owners
    0.65
     Jiří
    0.64
    THIS
    0.63
    Managing
    0.61
    मुख्य
    0.61
    𝗪
    0.61
    Lorem
    0.60
    POSITIVE LOGITS
    து
    0.72
     violates
    0.66
     inability
    0.64
    ensão
    0.64
    ção
    0.63
     olması
    0.63
    ية
    0.63
     abnormally
    0.63
     употреб
    0.61
     violate
    0.59
    Activations Density 0.007%

    No Known Activations