© 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. 34-GEMMASCOPE-RES-131K
    7. 30288
    Prev
    Next
    INDEX
    Explanations

    honors and privileges

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

    This neuron detects positive evaluative or congratulatory language (words expressing favorable sentiment).

    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
    brunnen
    -0.80
    camy
    -0.77
    Де
    -0.76
    apia
    -0.76
    ató
    -0.75
     préférable
    -0.75
    我们
    -0.74
    üste
    -0.73
    beforeSend
    -0.73
    Header
    -0.72
    POSITIVE LOGITS
     honour
    3.69
     honor
    3.69
     privilege
    3.02
     honored
    2.97
     honoured
    2.84
    honor
    2.81
     честь
    2.58
     honors
    2.42
     Honour
    2.39
    privilege
    2.34
    Activations Density 0.029%

    No Known Activations