© 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. 10-GEMMASCOPE-RES-131K
    7. 72470
    Prev
    Next
    INDEX
    Explanations

    'cause / coz explanation

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

    The neuron fires on informal causal conjunctions (especially “’cause”/“cause”) in the text.

    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
    疍
    -2.17
    镡
    -2.17
    ⼥
    -2.09
     anledning
    -2.06
     occaf
    -2.06
    广西
    -2.03
     вси
    -1.99
    ↑↑↑</
    -1.91
     bolster
    -1.90
     ผ้า
    -1.89
    POSITIVE LOGITS
    and
    2.27
    ll
    2.22
     we
    2.19
     anerkannt
    2.13
    ↵
    2.13
     selben
    2.06
    nitř
    1.94
     Lernen
    1.94
     imma
    1.87
     duże
    1.87
    Activations Density 0.004%

    No Known Activations