© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 70914
    Prev
    Next
    INDEX
    Explanations

    determine or comment

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

    The neuron mainly picks out numeric tokens—numbers, counts, rankings, measurements, etc.—wherever they occur 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_22/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
     manuten
    -1.83
     célè
    -1.83
     favoris
    -1.79
    Toujours
    -1.73
     éta
    -1.73
     bascul
    -1.68
     rése
    -1.68
    Rés
    -1.65
    Parmi
    -1.65
    Entrée
    -1.64
    POSITIVE LOGITS
     only
    1.85
     also
    1.76
     even
    1.66
    L
    1.65
     D
    1.64
     A
    1.55
     while
    1.52
    N
    1.52
     J
    1.48
     R
    1.48
    Activations Density 0.069%

    No Known Activations