© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72313
    Prev
    Next
    INDEX
    Explanations

    game losses

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

    The neuron fires on words and phrases that signal a team’s defeat—e.g. “loss,” “dropping,” “stumble,” “come to an end”—marking sporting losses.

    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
     refroidissement
    -1.70
    ÁRIO
    -1.66
    HasIndex
    -1.63
     帶
    -1.62
    Efter
    -1.60
    剮
    -1.59
    Zeneca
    -1.58
     burbu
    -1.57
    Following
    -1.55
    ргани
    -1.55
    POSITIVE LOGITS
     to
    2.44
    2
    2.14
     in
    2.09
     on
    1.91
    ↵
    1.88
    -
    1.77
     but
    1.74
     $
    1.71
    it
    1.66
    \
    1.63
    Activations Density 0.028%

    No Known Activations