© 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. 73347
    Prev
    Next
    INDEX
    Explanations

    scrolling content

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

    The neuron fires on words describing scrolling or similar document‐navigation actions (e.g. “scrolling,” “scroll,” “through”).

    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
    It
    -1.92
     Undoubtedly
    -1.90
     NEVER
    -1.87
     Ironically
    -1.86
     STILL
    -1.84
    躥
    -1.83
    即使
    -1.83
     Surprisingly
    -1.79
    جميع
    -1.78
     Additionally
    -1.77
    POSITIVE LOGITS
    ೢ
    2.80
     '
    2.59
    ᕮ
    2.48
    刄
    2.41
    ৢ
    2.28
    ”？
    2.28
    眚
    2.23
    ꜄
    2.23
    喾
    2.22
    榇
    2.19
    Activations Density 0.010%

    No Known Activations