© 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. 22-GEMMASCOPE-RES-131K
    7. 15274
    Prev
    Next
    INDEX
    Explanations

    Names, questions, and tags

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

    The neuron is triggered by tokens that look like angle-bracketed numeric tags (e.g. “<398”, “<856”, “<1176”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     its
    -1.37
     作り方
    -1.31
     desfile
    -1.30
    olio
    -1.23
    meja
    -1.23
     soyez
    -1.22
     olje
    -1.22
    fiore
    -1.20
    贋
    -1.18
    tasse
    -1.17
    POSITIVE LOGITS
    u
    1.37
    al
    1.21
    op
    1.20
    He
    1.13
    le
    1.12
    or
    1.12
     obicei
    1.06
    ///</
    1.05
    el
    1.05
    st
    1.05
    Activations Density 0.000%

    No Known Activations