© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64546
    Prev
    Next
    INDEX
    Explanations

    locations, components, or roles followed by 'for'

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

    The neuron fires most strongly on nouns naming endpoints or agents (e.g. users, sites, centers, systems, servers, organizations) that receive or process information.

    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
     suminist
    -1.03
    を入
    -1.00
     lámpara
    -0.98
     otorg
    -0.91
     suministro
    -0.91
     both
    -0.90
     matériaux
    -0.89
     trakcie
    -0.87
     Aktivität
    -0.86
     cả
    -0.86
    POSITIVE LOGITS
     for
    2.45
     who
    1.78
     where
    1.77
    เพื่อ
    1.55
     via
    1.45
     so
    1.31
     whence
    1.19
     affinch
    1.19
     quien
    1.17
     to
    1.16
    Activations Density 0.140%

    No Known Activations