© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14009
    Prev
    Next
    INDEX
    Explanations

    numbers with units and error bars

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

    This neuron never activates—it appears to be effectively “dead” and doesn’t detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     that
    -1.82
     where
    -1.45
     to
    -1.45
    antiago
    -1.43
    
    -1.38
    ఽ
    -1.34
    
    -1.34
    做一个
    -1.30
     股份
    -1.28
    partly
    -1.28
    POSITIVE LOGITS
    Since
    1.86
    There
    1.84
    3
    1.68
    During
    1.62
    １
    1.60
    ＆
    1.52
     Jumlah
    1.50
    Because
    1.49
    ２
    1.49
    "،
    1.48
    Activations Density 0.048%

    No Known Activations