© 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. 78688
    Prev
    Next
    INDEX
    Explanations

    patent application or disclosure

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

    The neuron activates on numeric tokens (e.g. digits, patent or version 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_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
    branding
    -0.75
    スン
    -0.73
    bark
    -0.70
    ᱚ
    -0.69
    acier
    -0.69
    buri
    -0.69
     نمک
    -0.66
    汞
    -0.66
    universal
    -0.65
    orch
    -0.65
    POSITIVE LOGITS
    郝
    0.78
    Jesús
    0.76
    ⢀
    0.75
    utado
    0.74
     actuación
    0.69
     extinct
    0.69
    梦见
    0.69
     (){
    0.69
    ډ
    0.69
     pastor
    0.69
    Activations Density 0.086%

    No Known Activations