© 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. 34-GEMMASCOPE-RES-131K
    7. 65230
    Prev
    Next
    INDEX
    Explanations

    Scout merit badge camping

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

    The neuron detects Boy Scouts–related announcements and references (e.g. “Scout Meeting,” “merit badge,” dates of Scout events).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    աստ
    -0.88
     Schloß
    -0.73
    REACH
    -0.73
     children
    -0.72
    莅
    -0.71
    Wein
    -0.71
    องค์
    -0.71
    要想
    -0.71
    Enf
    -0.71
     coel
    -0.70
    POSITIVE LOGITS
     knots
    0.82
    Patch
    0.77
     Patch
    0.77
     patch
    0.73
    bona
    0.73
    を加
    0.72
     patches
    0.72
     hikes
    0.71
     merit
    0.70
     buono
    0.70
    Activations Density 0.017%

    No Known Activations