© 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. 25322
    Prev
    Next
    INDEX
    Explanations

    numbers and file paths

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

    The neuron spotlights isolated numeric tokens (individual 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
    があります
    -1.76
    <bos>
    -1.63
    などの
    -1.56
    を
    -1.55
    がある
    -1.54
    もあります
    -1.52
    がありますが
    -1.49
    も
    -1.45
    と
    -1.45
    などを
    -1.42
    POSITIVE LOGITS
    咳咳
    1.30
    に変更
    1.28
    ことが
    1.26
     that
    1.25
    んですが
    1.23
    咦
    1.21
    んですよね
    1.18
    づけ
    1.16
    哎呀
    1.14
    為に
    1.13
    Activations Density 0.082%

    No Known Activations