© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119163
    Prev
    Next
    INDEX
    Explanations

    political or legislative districts

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

    The neuron detects citation‐style metadata elements—especially digit sequences (years, ISSN numbers, reference IDs) and the accompanying uppercase headings.

    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
     assessment
    -0.75
     assessing
    -0.71
     Liz
    -0.71
     roślin
    -0.66
     Anterior
    -0.65
    plasia
    -0.65
    idung
    -0.64
     khóc
    -0.64
     eliminating
    -0.63
    Hierarchy
    -0.63
    POSITIVE LOGITS
     tabled
    0.87
    ECG
    0.83
     Referral
    0.81
     Frye
    0.79
     cartera
    0.79
     inquire
    0.79
     gyne
    0.79
     MiG
    0.79
     parliament
    0.77
     Gek
    0.77
    Activations Density 0.017%

    No Known Activations