© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9456
    Prev
    Next
    INDEX
    Explanations

    cash incentives or report imprisonment

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

    The neuron fires on words naming or describing governmental or legal authority and actions (e.g. administration, control, amend, Act, authority).

    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
     пароль
    -1.20
     nieco
    -1.16
     wyłą
    -1.15
     thoughtful
    -1.14
     correct
    -1.12
    cemia
    -1.09
     honest
    -1.09
    \
    -1.07
     ਤ
    -1.06
     także
    -1.04
    POSITIVE LOGITS
    所谓
    1.33
     "
    1.30
     “
    1.29
     gabinete
    1.26
    parently
    1.24
    licopter
    1.23
     centaines
    1.23
     khawatir
    1.23
     allerlei
    1.21
     menatap
    1.17
    Activations Density 0.088%

    No Known Activations