© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77540
    Prev
    Next
    INDEX
    Explanations

    seeking approval

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

    This neuron identifies language soliciting or requiring someone’s support, consent, or participation (e.g. calls to “seek your help,” “require unanimous consent,” or similar requests).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    キル
    -0.79
     hakkında
    -0.77
    腹部
    -0.75
    }
    -0.73
     diversidad
    -0.73
     yardımcı
    -0.72
     poš
    -0.71
     Opportunities
    -0.71
    簡易
    -0.69
     reliever
    -0.69
    POSITIVE LOGITS
     support
    2.52
     cooperation
    2.50
     approval
    2.45
     consent
    2.44
     assistance
    2.42
     participation
    2.22
     involvement
    2.17
     help
    2.08
     permission
    1.91
     blessing
    1.85
    Activations Density 0.048%

    No Known Activations