© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103469
    Prev
    Next
    INDEX
    Explanations

    specific nouns and their states

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

    The neuron selectively fires on uppercase abbreviations or acronyms (initialisms) in the text.

    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
     manquer
    -1.60
     drenaje
    -1.58
     armazenamento
    -1.49
    榦
    -1.49
     wanting
    -1.48
     manguera
    -1.48
    なんですよ
    -1.47
     manifestaciones
    -1.44
     almohada
    -1.44
     kumaş
    -1.43
    POSITIVE LOGITS
     and
    2.11
     as
    1.70
     in
    1.59
     for
    1.48
     on
    1.41
     or
    1.37
     is
    1.36
     where
    1.33
     to
    1.32
     \&
    1.32
    Activations Density 0.200%

    No Known Activations