© 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. 84075
    Prev
    Next
    INDEX
    Explanations

    excited to announce

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

    This neuron detects upbeat announcement or promotional phrases expressing enthusiasm (e.g. “we are excited to,” “is delighted to,” “is proud to”).

    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
     to
    -1.76
    勦
    -1.56
     Either
    -1.55
     entweder
    -1.52
    Життєпис
    -1.52
     Certainly
    -1.50
     either
    -1.49
     sämtliche
    -1.48
     jeweiligen
    -1.47
    谂
    -1.42
    POSITIVE LOGITS
     also
    1.77
    this
    1.67
     этому
    1.65
     этот
    1.54
    龊
    1.53
     and
    1.47
    パートナー
    1.46
    応募
    1.41
     quae
    1.41
    DUR
    1.38
    Activations Density 0.011%

    No Known Activations