© 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. 33315
    Prev
    Next
    INDEX
    Explanations

    professions and fields

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

    The neuron is detecting domain- or profession-specific keywords (e.g. specialties, industries, or technical fields).

    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
     other
    -1.60
     might
    -1.20
     insufficient
    -1.19
     your
    -1.16
     employees
    -1.15
     arrangements
    -1.14
     to
    -1.12
     cantidades
    -1.12
     expresa
    -1.11
     important
    -1.10
    POSITIVE LOGITS
     principalement
    1.37
    توضیحات
    1.35
     również
    1.31
    Тел
    1.26
     tiež
    1.26
    Descriere
    1.21
    erdings
    1.19
     作り方
    1.16
    rischen
    1.15
     and
    1.14
    Activations Density 0.047%

    No Known Activations