© 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. 22-GEMMASCOPE-RES-131K
    7. 25491
    Prev
    Next
    INDEX
    Explanations

    start of quoted text fragments

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

    The neuron predominantly activates on numeric tokens and ellipsis‐style punctuation (e.g. sequences of dots).

    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
    ATIVA
    -1.31
    UCIÓN
    -1.30
    quelize
    -1.28
    vää
    -1.27
    Ár
    -1.20
    cửa
    -1.19
    ᠁
    -1.18
     emosi
    -1.16
    amkeit
    -1.16
    förm
    -1.16
    POSITIVE LOGITS
    -
    1.64
    '
    1.45
    ’
    1.29
    </i>
    1.28
     [
    1.25
    ...
    1.25
    大丈夫です
    1.22
    [
    1.17
    ..
    1.16
    .,
    1.15
    Activations Density 0.005%

    No Known Activations