© 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. 128070
    Prev
    Next
    INDEX
    Explanations

    The neuron flags markup or formatting delimiters—characters like “<”, “>”, and “\” that introduce or close HTML tags or LaTeX commands.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    special education, general solution, consumer sentiments

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    haviours
    -1.64
     cedera
    -1.42
     in
    -1.40
    angkap
    -1.38
     diinginkan
    -1.34
    tvguide
    -1.28
     épouse
    -1.27
     évé
    -1.27
    сение
    -1.27
     mengucap
    -1.25
    POSITIVE LOGITS
    /
    1.37
    '
    1.33
     magnificent
    1.25
     öst
    1.24
     his
    1.22
    o
    1.21
    &
    1.21
    不妨
    1.20
     луч
    1.17
    d
    1.17
    Activations Density 0.000%

    No Known Activations