© 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. 129466
    Prev
    Next
    INDEX
    Explanations

    The neuron flags tokens around public‐meeting invitations and calls for public comment (e.g. “public,” “open house,” “attend,” “comment”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    public comments and hearings

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     fendi
    -1.13
     ویتامین
    -1.10
     سینم
    -1.07
     گیاه
    -1.07
     сахара
    -1.06
     растений
    -1.03
     systemctl
    -1.02
    :
    -1.02
     inapropiados
    -1.01
     растение
    -1.00
    POSITIVE LOGITS
    וּ
    1.65
    ַּ
    1.63
    ּוֹ
    1.56
    ִּ
    1.52
    ֶּ
    1.44
     бампер
    1.43
    ֵּ
    1.29
     about
    1.27
     каба
    1.27
     máscara
    1.26
    Activations Density 0.035%

    No Known Activations