© 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. 112722
    Prev
    Next
    INDEX
    Explanations

    food and money

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

    The neuron is a general detector for content nouns (especially mass‐ or slang‐style nouns and informal noun tokens).

    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
    焄
    -1.63
     fabricación
    -1.57
     reparación
    -1.50
    jaqueta
    -1.50
     یا
    -1.49
     tyto
    -1.45
     uscita
    -1.42
    ...'
    -1.42
     anhänger
    -1.41
     $\&$
    -1.41
    POSITIVE LOGITS
    ll
    1.74
    genheiten
    1.54
     همان
    1.47
    can
    1.46
    is
    1.46
     then
    1.43
    Alongside
    1.41
    𖣘
    1.41
    必要があります
    1.41
    vestream
    1.41
    Activations Density 0.367%

    No Known Activations