© 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. 41000
    Prev
    Next
    INDEX
    Explanations

    vast quantity

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

    The neuron fires on occurrences of the word “vast” (and its adverbial form “vastly”), i.e. it detects that specific term indicating large scale.

    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
    哢
    -2.06
    ᠩ
    -1.94
     Ouvrez
    -1.92
     servido
    -1.91
    Amical
    -1.91
     Obtén
    -1.89
     gratuitas
    -1.88
     governs
    -1.88
     Commencez
    -1.87
    shimano
    -1.87
    POSITIVE LOGITS
    f
    2.73
    c
    2.61
    t
    2.56
    s
    2.56
    AN
    2.31
     "
    2.30
     tetapi
    2.27
     mais
    2.16
    es
    2.14
     namun
    2.11
    Activations Density 0.007%

    No Known Activations