© 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. 10-GEMMASCOPE-RES-131K
    7. 102929
    Prev
    Next
    INDEX
    Explanations

    originating from a place

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

    The neuron detects occurrences of “from” (and similar cues) marking a person’s place of origin in biographical or introductory contexts.

    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
     saying
    -1.57
    ？】
    -1.52
    klassi
    -1.35
    favorite
    -1.30
    weilen
    -1.28
    ニーカー
    -1.27
    favourite
    -1.27
    我が家
    -1.26
     patatas
    -1.26
     willkommen
    -1.26
    POSITIVE LOGITS
     its
    1.75
     =
    1.71
     can
    1.60
    不仅
    1.50
    !
    1.42
     therefore
    1.40
     quindi
    1.39
    //*[@
    1.39
     (…)
    1.33
     поэтому
    1.29
    Activations Density 0.037%

    No Known Activations