© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60480
    Prev
    Next
    INDEX
    Explanations

    all followed by quantity or summary

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

    This neuron detects summary phrases that start with “all,” (e.g. “In all, …”) marking overall totals or aggregate counts.

    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
     is
    -1.80
     about
    -1.65
     or
    -1.64
     &
    -1.63
    ’
    -1.59
     to
    -1.47
    」
    -1.43
     squadre
    -1.35
    b
    -1.33
    ”
    -1.33
    POSITIVE LOGITS
     accompagner
    1.72
     corrom
    1.70
    ญี่ป
    1.66
    
    1.65
    𓍊
    1.63
     remé
    1.60
    戽
    1.59
     aparência
    1.59
     malé
    1.57
     occuper
    1.55
    Activations Density 0.011%

    No Known Activations