© 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. 86943
    Prev
    Next
    INDEX
    Explanations

    location names

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

    The neuron fires on discourse-level connective words (e.g. “However,” “Thus,” “Additionally,” “Furthermore,” etc.) that signal logical or argumentative transitions.

    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
    饪
    -1.75
    䛗
    -1.63
     MotionEvent
    -1.59
    iſter
    -1.59
     BorderSide
    -1.55
     AdapterView
    -1.54
    餍
    -1.52
    ignment
    -1.48
     onPause
    -1.48
     enfermedades
    -1.46
    POSITIVE LOGITS
     können
    1.38
     also
    1.35
     無料
    1.33
     Бог
    1.30
    Furthermore
    1.30
     setiap
    1.30
     in
    1.27
     Hinsicht
    1.25
    ämään
    1.25
    很多
    1.25
    Activations Density 0.099%

    No Known Activations