© 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. 66857
    Prev
    Next
    INDEX
    Explanations

    tiled images

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

    This neuron activates on occurrences of “tile” or “tiled” (i.e. references to tiling or tile‐based content).

    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
    ↵
    -2.47
    ↵↵
    -2.27
    鋮
    -2.09
    袮
    -2.08
    d
    -2.00
    綃
    -1.86
     discernible
    -1.80
    o
    -1.77
    ↵↵↵↵
    -1.74
     Not
    -1.74
    POSITIVE LOGITS
    蛲
    2.14
    菹
    2.06
     gustar
    2.06
    很赞
    2.05
     sorprender
    2.02
     geheim
    1.96
     أنت
    1.94
    ὺς
    1.93
    ſam
    1.92
     considerados
    1.92
    Activations Density 0.005%

    No Known Activations