© 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. 102539
    Prev
    Next
    INDEX
    Explanations

    foreground objects and colors

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

    The neuron consistently activates on the exact word “foreground” (in any casing or context).

    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
    $
    -2.45
     هایی
    -2.36
     جدید
    -2.28
    稳定的
    -2.25
     आवश्यक
    -2.23
    ຼ
    -2.13
    SI
    -2.11
     chcą
    -2.09
     nejlepší
    -2.08
    We
    -2.06
    POSITIVE LOGITS
    ’
    2.80
    但是在
    2.80
    とその
    2.75
     Garantía
    2.73
    ers
    2.64
    “
    2.50
     dificuldades
    2.38
    ”
    2.38
    骉
    2.33
     Propiedad
    2.31
    Activations Density 0.012%

    No Known Activations