© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64285
    Prev
    Next
    INDEX
    Explanations

    addressing customer inquiries

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

    The neuron strongly activates on numeric tokens (digit sequences), i.e. standalone numbers or version‐style numbers.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    ॰
    -1.02
    也
    -0.94
    ️⃣
    -0.94
    kua
    -0.91
     also
    -0.91
    chenken
    -0.88
    ⃣
    -0.87
    cokinetics
    -0.87
     Order
    -0.84
    ἁ
    -0.82
    POSITIVE LOGITS
     登山
    0.93
     링크
    0.91
     befall
    0.87
     alkoholu
    0.86
     respondeu
    0.85
     vários
    0.82
    謫
    0.81
     évidemment
    0.79
    こちらは
    0.79
    Setiap
    0.79
    Activations Density 0.008%

    No Known Activations