© 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. 34-GEMMASCOPE-RES-131K
    4. 115726
    Prev
    Next
    INDEX
    Explanations

    scientific research citations

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

    technical and scientific terminology in academic or documentation contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on numeric tokens (e.g. IDs, counts, years, or other standalone 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
     berkata
    -0.77
    Cadastro
    -0.75
    含有
    -0.74
    ortage
    -0.73
     Healthcare
    -0.73
    кипедия
    -0.72
     healthcare
    -0.71
    
    -0.70
    cle
    -0.70
     maaaring
    -0.70
    POSITIVE LOGITS
     CGI
    1.28
    cgi
    1.05
     scientists
    1.05
     research
    1.05
    IAR
    0.89
     Consultative
    0.86
    üste
    0.84
    гло
    0.82
    research
    0.82
    CG
    0.82
    Activations Density 0.015%

    No Known Activations