© 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. 102865
    Prev
    Next
    INDEX
    Explanations

    objects with linked items

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

    The neuron fires most strongly on numeric literals (i.e. sequences of digits) in code or JSON snippets.

    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
     oktober
    -0.90
     pertes
    -0.86
    künfte
    -0.82
     profil
    -0.80
     इस्त
    -0.80
     sár
    -0.79
    вич
    -0.79
    IZE
    -0.79
     policiers
    -0.79
     amplitude
    -0.79
    POSITIVE LOGITS
     attachments
    1.58
     related
    1.52
     accessories
    1.49
    related
    1.48
     images
    1.37
     photos
    1.30
     pictures
    1.29
     children
    1.27
     associated
    1.24
     photographs
    1.20
    Activations Density 0.058%

    No Known Activations