© 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. 10-GEMMASCOPE-RES-131K
    7. 65500
    Prev
    Next
    INDEX
    Explanations

    legal or illegal information/actions

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

    The neuron primarily detects words that signal legal context (e.g., “legal,” “illegal,” and related legality terms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    wendi
    -1.73
     aime
    -1.72
     kurios
    -1.60
    alties
    -1.59
     éx
    -1.56
    fromUtf
    -1.55
    omsday
    -1.52
     effets
    -1.48
    ients
    -1.47
     signes
    -1.46
    POSITIVE LOGITS
     what
    1.91
     it
    1.61
     and
    1.55
    0
    1.54
     Ersten
    1.47
     things
    1.44
    1
    1.43
     components
    1.41
     Of
    1.40
     operates
    1.38
    Activations Density 0.054%

    No Known Activations