© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104698
    Prev
    Next
    INDEX
    Explanations

    binary or ternary

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

    The neuron responds to technical terms ending in “-ary” that specify the number of components in a mixture or system (e.g. binary, ternary, quaternary).

    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
    那我
    -2.63
    cursions
    -2.41
    gemeen
    -2.38
     ook
    -2.34
    苤
    -2.28
     Which
    -2.23
    耜
    -2.20
     auch
    -2.17
    ሖ
    -2.16
    不
    -2.14
    POSITIVE LOGITS
    e
    3.48
    ization
    2.52
    //
    2.31
    you
    2.22
     入っ
    2.19
    目前的
    2.17
    where
    2.06
    )$
    2.05
     gratuito
    2.02
    and
    2.00
    Activations Density 0.016%

    No Known Activations