© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42502
    Prev
    Next
    INDEX
    Explanations

    URLs and technical specifications

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

    This neuron fires on capitalized or title‐case tokens—like section or article headings, product and model names, acronyms, and other proper‐name or technical‐term tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     from
    -2.06
     these
    -1.81
     this
    -1.59
    these
    -1.44
     These
    -1.39
     both
    -1.32
    phoric
    -1.27
     though
    -1.27
     however
    -1.25
     each
    -1.20
    POSITIVE LOGITS
     $
    1.17
    荩
    1.14
    䡲
    1.13
    вайтесь
    1.05
     Çünkü
    1.03
    getSupport
    1.03
     Ayrıca
    1.02
    áře
    1.02
     also
    1.02
    ["
    1.02
    Activations Density 0.369%

    No Known Activations