© 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. 22-GEMMASCOPE-RES-131K
    7. 73554
    Prev
    Next
    INDEX
    Explanations

    reputation, opinion, and quality

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

    The neuron fires on abstract, evaluative or qualitative terms—nouns (and related forms) denoting perceptions, conditions, reputations, aspects or qualities.

    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
    "}\
    -0.86
     meglio
    -0.85
     sometime
    -0.82
    NOSTIC
    -0.82
    łaty
    -0.81
     bleibt
    -0.81
     vergleichen
    -0.80
     based
    -0.79
    大佬
    -0.79
     Pueden
    -0.78
    POSITIVE LOGITS
     ensuring
    1.09
     matters
    1.06
    quality
    0.95
     détail
    0.95
    Reputation
    0.94
    idste
    0.93
     who
    0.92
     Reputation
    0.86
     reputation
    0.86
     outcomes
    0.85
    Activations Density 0.043%

    No Known Activations