© 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. 34-GEMMASCOPE-RES-131K
    7. 78026
    Prev
    Next
    INDEX
    Explanations

    GNU General Public License

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

    The neuron activates on numeric tokens—digits, measurements, version numbers, and other standalone numbers—throughout the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     eingesetzt
    -0.90
    ederen
    -0.72
     Suz
    -0.70
    ิลปะ
    -0.69
    wers
    -0.69
     TRAP
    -0.69
    וף
    -0.69
     ahead
    -0.69
    thulhu
    -0.69
    纥
    -0.69
    POSITIVE LOGITS
    隕
    0.74
    小川
    0.72
     梨
    0.68
    LHS
    0.65
     elegancia
    0.64
     حضرت
    0.63
    死了
    0.63
    ATG
    0.63
     ε
    0.63
     capacit
    0.62
    Activations Density 0.019%

    No Known Activations