© 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. 128394
    Prev
    Next
    INDEX
    Explanations

    pressure on

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

    This neuron primarily activates on the word “on.”

    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
    yit
    -1.73
    ragamo
    -1.71
    ὺς
    -1.70
    旆
    -1.70
    mpo
    -1.70
     Приступљено
    -1.67
    linawan
    -1.63
    絝
    -1.63
    mpagne
    -1.61
    yyv
    -1.60
    POSITIVE LOGITS
    b
    2.17
    0
    2.02
    As
    1.96
    s
    1.96
     for
    1.91
    c
    1.90
    f
    1.88
    j
    1.85
    al
    1.82
    p
    1.81
    Activations Density 0.010%

    No Known Activations