© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99436
    Prev
    Next
    INDEX
    Explanations

    electorate or perovskites

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

    The neuron flags rare, technical or formal multi‐syllable nouns (e.g. specialized material names like “perovskite” and formal terms like “electorate”).

    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
     firft
    -2.52
    氲
    -2.45
     juft
    -2.42
     whofe
    -2.41
     lakini
    -2.38
     CALIFORNI
    -2.34
     ftate
    -2.28
     gustado
    -2.16
    較
    -2.16
     fhall
    -2.13
    POSITIVE LOGITS
    n
    3.14
     he
    2.94
    Ã
    2.75
    “
    2.72
    ity
    2.64
    ,"
    2.61
    :"
    2.50
    er
    2.44
    
    2.42
     wybran
    2.38
    Activations Density 0.010%

    No Known Activations