© 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. 128166
    Prev
    Next
    INDEX
    Explanations

    disillusionment or dissatisfaction

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

    The neuron flags words beginning with the prefix “dis-” that express negative states (e.g. disillusion, dissatisfied, disaffection).

    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
    膾
    -1.96
     skupina
    -1.80
     selben
    -1.79
    狃
    -1.73
    ご理解
    -1.70
     generan
    -1.70
     inš
    -1.70
    mpagne
    -1.70
     escrito
    -1.69
    斗争
    -1.69
    POSITIVE LOGITS
    所以在
    1.70
    henswürdigkeiten
    1.69
    for
    1.67
    To
    1.60
    }
    1.58
    не
    1.50
    glected
    1.49
    鹩
    1.48
    我们的
    1.47
    结语
    1.46
    Activations Density 0.007%

    No Known Activations