© 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. 22-GEMMASCOPE-RES-131K
    7. 38948
    Prev
    Next
    INDEX
    Explanations

    true or false conditions

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

    The neuron fires on variable‐to‐constant assignment expressions (i.e. when a variable is set equal to a literal).

    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
     annet
    -1.00
    änglich
    -1.00
     также
    -0.99
    ograft
    -0.98
    uglify
    -0.96
     recently
    -0.94
    recently
    -0.94
    と思っている
    -0.92
    avir
    -0.92
    ribune
    -0.91
    POSITIVE LOGITS
    epam
    1.03
    biker
    0.98
     phố
    0.97
    kově
    0.96
     true
    0.96
    Dawg
    0.94
    (;;)
    0.94
     triliun
    0.93
    ."
    0.92
    zień
    0.92
    Activations Density 0.001%

    No Known Activations