© 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. 22-GEMMASCOPE-RES-131K
    7. 33118
    Prev
    Next
    INDEX
    Explanations

    abstract/technical concepts

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

    The neuron fires on content-bearing words (mostly technical or informative nouns and adjectives) rather than on function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ViewFeatures
    -1.07
     addirittura
    -1.06
    intelligible
    -1.03
    agles
    -1.01
     gostaria
    -1.00
    だけではなく
    -0.99
    leopard
    -0.98
    つづく
    -0.97
     aplicativos
    -0.96
    以外にも
    -0.94
    POSITIVE LOGITS
     usually
    1.23
    examples
    1.20
     encantó
    1.19
     is
    1.17
     cortas
    1.16
    stående
    1.13
    典型
    1.12
     or
    1.08
     españolas
    1.08
    example
    1.06
    Activations Density 0.067%

    No Known Activations