© 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. 324
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by common articles

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

    The neuron activates on numeric measurement tokens—especially numbers (often with decimal points) indicating quantities or values.

    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
    ,
    -1.40
    c
    -1.34
    f
    -1.34
     многих
    -1.34
    n
    -1.31
     by
    -1.31
    d
    -1.30
    j
    -1.27
    u
    -1.26
    O
    -1.23
    POSITIVE LOGITS
     the
    1.53
     ་
    1.31
    泚
    1.28
     them
    1.23
     faſt
    1.21
     systém
    1.20
     srd
    1.20
     dezelve
    1.19
     acteur
    1.18
     ajoute
    1.17
    Activations Density 0.074%

    No Known Activations