© 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. 13968
    Prev
    Next
    INDEX
    Explanations

    product details, trading shares

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

    The neuron flags the main content-bearing words (key nouns and verbs) in each snippet rather than 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
     soldat
    -1.70
     bricola
    -1.55
    ܖ
    -1.45
     discours
    -1.43
     formulaire
    -1.43
     basque
    -1.41
     horloge
    -1.38
     ailes
    -1.38
     bilan
    -1.37
     obtenir
    -1.36
    POSITIVE LOGITS
     this
    1.97
     any
    1.91
    This
    1.73
     cualquier
    1.44
     einzelnen
    1.43
     raczej
    1.41
     это
    1.41
     This
    1.39
     these
    1.38
     with
    1.37
    Activations Density 0.117%

    No Known Activations