© 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. 22-GEMMASCOPE-RES-131K
    4. 54042
    Prev
    Next
    INDEX
    Explanations

    unchanging or permanent states

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

    The neuron fires on words that express fixedness or permanence (e.g. “fixed,” “permanent,” “guaranteed,” “finite,” “remains”), i.e. tokens signaling unchanging or lasting properties.

    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
     вместо
    -1.20
     but
    -1.05
    なのは
    -1.01
     jeszcze
    -0.99
     yet
    -0.96
    yet
    -0.94
     new
    -0.93
    Răspunde
    -0.92
     Yet
    -0.91
     in
    -0.90
    POSITIVE LOGITS
     unless
    1.41
     uan
    1.20
     until
    1.20
    regardless
    1.16
    unless
    1.16
     forever
    1.14
     навсегда
    1.13
    Unless
    1.11
    除非
    1.08
     nobody
    1.07
    Activations Density 0.068%

    No Known Activations