© 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. 42214
    Prev
    Next
    INDEX
    Explanations

    plank, Planck, slats

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

    The neuron detects occurrences of the substring “plank” (in any case), whether in the common noun “plank” or the proper name “Planck.”

    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
     ſch
    -2.55
     unſ
    -2.34
    はありません
    -2.34
    ㌘
    -2.22
    きましたが
    -2.22
    
    -2.20
     Répondre
    -2.20
     Quelques
    -2.17
    焿
    -2.16
     Anſ
    -2.14
    POSITIVE LOGITS
    er
    2.84
    "
    2.73
    K
    2.64
    man
    2.64
    𓋼
    2.61
    N
    2.59
    耵
    2.53
     "
    2.39
    D
    2.38
    '
    2.34
    Activations Density 0.003%

    No Known Activations