© 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. 43929
    Prev
    Next
    INDEX
    Explanations

    filtering

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

    The main thing this neuron does is detect occurrences of the word “filtering.”

    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
    s
    -3.25
    e
    -2.53
    en
    -2.45
     ก็
    -2.44
    ↵↵
    -2.42
     we
    -2.31
    ano
    -2.16
    枫
    -2.16
     шанс
    -2.13
     Get
    -2.08
    POSITIVE LOGITS
    囖
    3.27
    𐐀
    3.22
    脔
    2.75
    0
    2.72
    阄
    2.70
     verschied
    2.69
    𐀀
    2.66
     gröss
    2.64
    This
    2.64
    jemahan
    2.61
    Activations Density 0.007%

    No Known Activations