© 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. 317
    Prev
    Next
    INDEX
    Explanations

    sections or introductions

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

    The neuron fires strongly on standalone numeric tokens (counts, codes, or measurements) 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
     nació
    -1.32
     工房
    -1.29
     måneder
    -1.29
     intensif
    -1.27
     blom
    -1.27
     pérd
    -1.27
     literat
    -1.27
     GARANT
    -1.27
     constater
    -1.27
     obrazy
    -1.26
    POSITIVE LOGITS
     F
    1.56
     U
    1.52
    A
    1.45
     V
    1.45
     IT
    1.41
     d
    1.40
    "
    1.39
    F
    1.38
     J
    1.37
     .
    1.37
    Activations Density 0.000%

    No Known Activations