© 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. 107134
    Prev
    Next
    INDEX
    Explanations

    Philipp SalzIndia country names

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

    The neuron fires on numeric tokens—especially years, page and volume numbers, and other citation‐style numerals.

    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
     フォト
    -0.83
     welt
    -0.82
     resolução
    -0.79
    jątk
    -0.77
     solves
    -0.77
     microm
    -0.76
     mơ
    -0.72
     モダン
    -0.72
    jęcie
    -0.71
     slur
    -0.71
    POSITIVE LOGITS
    getClassLoader
    0.75
     downside
    0.74
    cenzo
    0.74
     Felipe
    0.73
     species
    0.73
     trăm
    0.72
     geographical
    0.71
     clothing
    0.71
     monopoly
    0.71
     shoots
    0.71
    Activations Density 0.021%

    No Known Activations