© 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. 39708
    Prev
    Next
    INDEX
    Explanations

    disclosed, hereby granted

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

    The neuron fires on verbs used in formal legal or administrative statements (e.g. “disclosed,” “granted,” “is available”).

    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
    tierte
    -1.16
    createCanvas
    -1.14
    桖
    -1.13
    ڧ
    -1.13
    тона
    -1.11
    barer
    -1.10
    elser
    -1.09
    eraus
    -1.09
    ФО
    -1.09
     spou
    -1.09
    POSITIVE LOGITS
    us
    1.04
     here
    1.02
    on
    1.02
    épisode
    1.02
     if
    1.02
     nordrhein
    1.00
     now
    0.99
     M
    0.99
    าก็
    0.98
     L
    0.97
    Activations Density 0.000%

    No Known Activations