© 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. 22-GEMMASCOPE-RES-131K
    7. 104623
    Prev
    Next
    INDEX
    Explanations

    possibly or

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

    The neuron fires strongly on words naming physical substances or materials (e.g. plaster, chalk, alcohol, mercury, prototype).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ꯱
    -1.19
     Ministre
    -1.18
    がる
    -1.18
     duran
    -1.16
    UNDA
    -1.11
     kanker
    -1.09
     ibang
    -1.09
     >
    -1.09
     procra
    -1.07
    ##
    -1.06
    POSITIVE LOGITS
     or
    3.59
     possibly
    2.03
     but
    1.99
     perhaps
    1.90
     maybe
    1.73
     или
    1.64
     because
    1.61
     hoặc
    1.54
     although
    1.53
     либо
    1.50
    Activations Density 0.057%

    No Known Activations