© 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. 67590
    Prev
    Next
    INDEX
    Explanations

    pre-order, measuring brain, /* copyright

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

    The neuron never activates—it doesn’t respond to any tokens.

    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
     hjælpe
    -1.07
     belga
    -1.02
     academic
    -1.02
    楪
    -1.02
     prado
    -1.02
    Toma
    -1.02
    車が
    -1.00
     same
    -1.00
     malla
    -0.99
    Gps
    -0.98
    POSITIVE LOGITS
     иллюстрация
    1.15
     ファー
    1.14
     inmediatamente
    1.10
    会导致
    1.09
    return
    1.09
    Einf
    1.05
    沪
    1.03
     uusi
    1.02
    lamydia
    1.02
     yılında
    1.02
    Activations Density 0.000%

    No Known Activations