© 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. 54142
    Prev
    Next
    INDEX
    Explanations

    explaining variants or descriptions

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

    The neuron is keyed to numeric literals (especially decimal or integer constants) in code.

    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
    thumbsup
    -0.96
    rofl
    -0.90
     locatie
    -0.89
     opciones
    -0.88
    umentar
    -0.85
     серый
    -0.85
     Pb
    -0.85
    consum
    -0.85
    晝
    -0.84
     такой
    -0.83
    POSITIVE LOGITS
     what
    0.90
     TAMBÉM
    0.88
     can
    0.86
    estre
    0.82
    date
    0.81
    alleros
    0.81
    мость
    0.79
    برها
    0.79
     tanda
    0.78
    melho
    0.78
    Activations Density 0.002%

    No Known Activations