© 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. 10-GEMMASCOPE-RES-131K
    7. 40385
    Prev
    Next
    INDEX
    Explanations

    medical, technical, or scientific terms

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

    technical or scientific terms, especially those related to measurement, equipment, and materials.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on content‐bearing words—especially nouns and adjectives denoting objects or concepts—while ignoring 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_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
     we
    -1.48
    marché
    -1.40
     bandeau
    -1.39
    isdir
    -1.33
     messaggi
    -1.32
     to
    -1.30
     jezelf
    -1.29
     każde
    -1.29
     segíts
    -1.28
     jesteśmy
    -1.27
    POSITIVE LOGITS
    -
    2.22
     i
    1.44
    f
    1.41
    "
    1.40
     first
    1.30
     portuguesa
    1.25
    irect
    1.23
    ngilizce
    1.23
    訛
    1.21
     ersche
    1.20
    Activations Density 0.175%

    No Known Activations