© 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. 67515
    Prev
    Next
    INDEX
    Explanations

    pushing boundaries and limits

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

    The neuron detects phrases that describe pushing or testing the boundaries or limits of something.

    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
     Anſ
    -1.91
     suministros
    -1.70
    hmmmm
    -1.67
    ▪️
    -1.66
    ⤷
    -1.64
     accompagner
    -1.63
     distinguir
    -1.63
    <bos>
    -1.62
    
    -1.60
    Mvh
    -1.55
    POSITIVE LOGITS
     of
    2.92
     ,
    1.91
     even
    1.90
    ‘
    1.84
     in
    1.83
    $,
    1.70
    in
    1.70
    m
    1.70
     by
    1.61
    <i>
    1.60
    Activations Density 0.022%

    No Known Activations