© 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. 64478
    Prev
    Next
    INDEX
    Explanations

    Company registration information

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

    This neuron activates on numeric tokens (sequences of digits) such as years, identifiers, or other 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
    為に
    -1.37
    */,
    -1.09
    ʿ
    -1.02
    ₱
    -1.02
    ":{
    -0.99
     or
    -0.98
    ようです
    -0.97
     estimés
    -0.94
    炉
    -0.93
    cobacterium
    -0.93
    POSITIVE LOGITS
    が上が
    1.20
    方針
    1.19
    そうです
    1.19
    でしょうね
    1.16
     éducation
    1.16
    がありますが
    1.13
    恐れ
    1.12
    觔
    1.08
    んじゃ
    1.08
    ジナル
    1.06
    Activations Density 0.003%

    No Known Activations