© 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. 66808
    Prev
    Next
    INDEX
    Explanations

    describes what

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

    The neuron detects large numeric tokens—specifically multi-digit numbers such as three-digit counts or measurements.

    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
     kompati
    -1.81
    outros
    -1.56
    cardigan
    -1.51
    alain
    -1.51
     kabát
    -1.42
    langsung
    -1.41
    regalo
    -1.36
     نمی‌
    -1.35
     kvalit
    -1.32
     mieste
    -1.32
    POSITIVE LOGITS
    In
    1.49
    ha
    1.30
    in
    1.24
    Z
    1.23
    B
    1.23
    net
    1.22
    N
    1.21
    co
    1.20
    em
    1.20
    o
    1.19
    Activations Density 0.132%

    No Known Activations