© 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. 128202
    Prev
    Next
    INDEX
    Explanations

    This neuron lights up on self-referential profile phrases—especially place names and personal identity statements (e.g. “I’m a former Chicago guy,” “a Los Angeles valley girl,” “a Northerner from Florida,” etc.).

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

    regions and nationalities

    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
     such
    -1.23
     CURLOPT
    -1.17
     phím
    -1.09
     créer
    -1.06
     utaf
    -1.02
     البحث
    -1.02
    ଷ
    -1.02
     metus
    -1.01
    jenner
    -1.01
     zoals
    -1.00
    POSITIVE LOGITS
    Médaille
    1.30
    Both
    1.25
    Those
    1.23
     частности
    1.19
     excessive
    1.10
     gyvento
    1.09
    Despite
    1.08
     people
    1.07
     regional
    1.05
     作り方
    1.05
    Activations Density 0.053%

    No Known Activations