© 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. 68065
    Prev
    Next
    INDEX
    Explanations

    acronyms, titles, and beginnings of phrases

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

    The neuron detects numeric tokens—integers or decimals—wherever they appear 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
     “
    -1.95
     in
    -1.80
     by
    -1.73
     at
    -1.73
     an
    -1.72
     for
    -1.71
     the
    -1.63
     two
    -1.59
     can
    -1.59
     its
    -1.50
    POSITIVE LOGITS
    rédients
    1.66
     着物
    1.60
    孱
    1.59
    dhism
    1.54
     göm
    1.47
    ribune
    1.45
     utilizzare
    1.45
    </i>
    1.44
     offrant
    1.42
    黜
    1.42
    Activations Density 0.001%

    No Known Activations