© 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. 113145
    Prev
    Next
    INDEX
    Explanations

    chi prefix

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

    The neuron fires on every occurrence of the three‐letter sequence “Chi” (e.g. as the start of names or terms beginning with “Chi”).

    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
    ↵↵
    -3.28
    秾
    -2.77
    ’?
    -2.67
    ’-
    -2.55
     acostumb
    -2.52
    ’.”
    -2.39
     estes
    -2.38
    鏨
    -2.36
     ‘’
    -2.36
    ↵
    -2.34
    POSITIVE LOGITS
    ised
    2.98
    ization
    2.67
    ～♪
    2.55
    炬
    2.47
     शुर
    2.44
    KommentareTeilen
    2.42
    erintah
    2.41
    ሷ
    2.38
    ～！
    2.33
    仉
    2.33
    Activations Density 0.005%

    No Known Activations