© 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. 10-GEMMASCOPE-RES-131K
    7. 48330
    Prev
    Next
    INDEX
    Explanations

    "foo" "Bar" "world" "OK"

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

    The neuron is triggered by literal text strings (especially UI labels/buttons) inside quotes—i.e. it spots quoted text values assigned to user-interface elements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    惬
    -1.68
     câmera
    -1.63
    质感
    -1.63
    细腻
    -1.57
    ‪.
    -1.52
    妩
    -1.50
    浓郁
    -1.49
     fermer
    -1.44
    ִּ
    -1.44
    他們
    -1.44
    POSITIVE LOGITS
     of
    2.67
     for
    2.36
     to
    2.30
     as
    2.25
     from
    2.25
     while
    2.14
     if
    1.70
     with
    1.69
     like
    1.68
     before
    1.67
    Activations Density 0.004%

    No Known Activations