© 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. 128586
    Prev
    Next
    INDEX
    Explanations

    The neuron detects occurrences of the word “place.”

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

    a place where

    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
    鹟
    -2.53
    事が
    -2.48
    妧
    -2.45
     continúas
    -2.42
    艫
    -2.39
    蚴
    -2.34
    粁
    -2.28
     Garantía
    -2.23
     cómod
    -2.16
     Gedanke
    -2.13
    POSITIVE LOGITS
     или
    2.50
     oder
    2.41
    in
    2.39
    ,’’
    2.25
    También
    2.22
     where
    2.16
     sia
    2.09
     (
    2.06
    或
    2.05
     atau
    2.00
    Activations Density 0.016%

    No Known Activations