© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7068
    Prev
    Next
    INDEX
    Explanations

    numbers and separators

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

    The neuron responds to standalone numeric tokens (e.g. dates, times, version or section 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_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
     Männern
    -2.47
    閹
    -2.42
     Berücksich
    -2.30
    鹋
    -2.28
     Umständen
    -2.23
    ⡪
    -2.23
    hogany
    -2.20
    apkan
    -2.20
    ᯾
    -2.20
     comical
    -2.16
    POSITIVE LOGITS
    (
    2.64
    I
    2.55
    n
    2.48
    m
    2.39
    O
    2.34
    b
    2.25
    ma
    2.22
    f
    2.20
    N
    2.19
    ad
    2.17
    Activations Density 0.071%

    No Known Activations