© 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. 128260
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on title- or heading-style phrases and the very first content words of distinct article or section intros.

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

    Lake Maggiore, Italian plays, flags

    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
    čni
    -1.12
    を行いました
    -1.04
    邉
    -1.02
    ktı
    -0.99
     data
    -0.99
    ׁ
    -0.98
    ण
    -0.95
     bauen
    -0.94
     interns
    -0.91
     rehearsals
    -0.91
    POSITIVE LOGITS
    rifft
    1.14
    titure
    1.13
     ویتامین
    1.12
    ！"
    1.10
    zept
    1.09
     erila
    1.09
     météo
    1.08
     Voiture
    1.08
     Matériau
    1.07
     परिवार
    1.06
    Activations Density 0.128%

    No Known Activations