© 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. 85986
    Prev
    Next
    INDEX
    Explanations

    a/an followed by a word

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

    This neuron selectively activates on numeric tokens (digits and measurements, including decimals).

    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
     about
    -1.67
    eronau
    -1.28
    終於
    -1.24
     někter
    -1.23
    ᓕ
    -1.16
    呦
    -1.15
    秋季
    -1.15
     its
    -1.15
     than
    -1.14
     only
    -1.13
    POSITIVE LOGITS
    ietal
    1.20
    НЫ
    1.18
     you
    1.16
     your
    1.16
     largeur
    1.10
     plateforme
    1.08
    НИЯ
    1.07
     یا
    1.02
    пев
    1.02
     σας
    1.01
    Activations Density 0.188%

    No Known Activations