© 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. 7146
    Prev
    Next
    INDEX
    Explanations

    practice of

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

    The neuron fires on words naming or describing the core action or practice in a definitional/explanatory context (e.g. “organisms,” “eliminate,” “practice,” “defecating”).

    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
     these
    -1.36
     even
    -1.26
     be
    -1.25
     also
    -1.19
     then
    -1.16
     it
    -1.13
    :
    -1.09
     thus
    -1.04
     each
    -1.02
     accordingly
    -1.02
    POSITIVE LOGITS
    的一种
    1.88
     Projektu
    1.46
    WillAppear
    1.44
    Either
    1.43
    usually
    1.35
    baliknya
    1.34
     sokak
    1.34
     Meksi
    1.33
    łóż
    1.28
     genellikle
    1.27
    Activations Density 0.287%

    No Known Activations