© 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. 35719
    Prev
    Next
    INDEX
    Explanations

    content, programs, documents, information, samples

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

    The neuron activates on numeric tokens (multi‐digit numbers).

    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
    ztes
    -1.28
     เ
    -1.25
     «
    -1.21
     acri
    -1.20
     opět
    -1.18
    man
    -1.16
     Wij
    -1.14
    voli
    -1.14
     to
    -1.14
    POSITIVE LOGITS
     Pristup
    1.69
     koneksi
    1.56
     certain
    1.48
     lettore
    1.44
     parachoque
    1.44
     produttore
    1.41
     cetak
    1.36
     ragazzo
    1.31
     Früchte
    1.30
     wiesz
    1.29
    Activations Density 0.183%

    No Known Activations