© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44733
    Prev
    Next
    INDEX
    Explanations

    to place names

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

    The neuron selectively activates on numeric tokens—especially decimal‐formatted figures—i.e. it’s picking up numbers 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_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
     męskie
    -1.52
    ↀ
    -1.50
     límites
    -1.49
    などで
    -1.48
     próximas
    -1.41
    ᐠ
    -1.41
     aéreas
    -1.41
     valori
    -1.38
     temáticas
    -1.38
     empleos
    -1.38
    POSITIVE LOGITS
    (
    1.63
     In
    1.59
     to
    1.59
     for
    1.57
    with
    1.55
    of
    1.40
    for
    1.38
    -
    1.38
    v
    1.36
    ar
    1.32
    Activations Density 0.035%

    No Known Activations