© 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. 22-GEMMASCOPE-RES-131K
    7. 38734
    Prev
    Next
    INDEX
    Explanations

    average and typical groups

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

    The neuron flags references to average or typical quantities or demographics—e.g. “the average X,” “typical Y,” “lay person,” “residential customer,” etc.

    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
     различни
    -1.68
     magnificent
    -1.45
     ブラウス
    -1.39
     crucial
    -1.37
    羮
    -1.36
     тази
    -1.35
    螃
    -1.34
    sthe
    -1.33
     shimmering
    -1.33
     renowned
    -1.32
    POSITIVE LOGITS
    Every
    1.45
     garner
    1.41
     there
    1.34
    Like
    1.33
     average
    1.30
    "
    1.30
    Being
    1.30
     what
    1.29
     often
    1.28
    It
    1.27
    Activations Density 0.016%

    No Known Activations