© 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. 38962
    Prev
    Next
    INDEX
    Explanations

    filling and filled

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

    The neuron activates on tokens that are variations of the root “fill” (e.g. fill, filling, filled, infill and even foreign‐language equivalents like preencher).

    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
    '
    -2.41
    .
    -2.38
    ti
    -2.28
     beginnings
    -2.28
    The
    -2.22
    亮相
    -2.14
     seleccionar
    -2.13
    -2.06
    [
    -2.06
     一个
    -2.06
    POSITIVE LOGITS
    
    2.55
    𓆜
    2.27
    歃
    2.27
    我对
    2.25
    鰾
    2.17
    鄠
    2.16
    鱨
    2.08
    羮
    2.06
    聼
    2.05
    我这
    2.03
    Activations Density 0.009%
    No Known Activations