© 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. 33251
    Prev
    Next
    INDEX
    Explanations

    mathematical equations or code snippets

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

    The neuron fires on literal constant tokens in code or configs—things like numeric literals, boolean/flag names, and other hard-coded values.

    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
     can
    -1.20
     The
    -1.17
     ähnlich
    -1.08
    dfn
    -1.02
     sebagainya
    -1.02
     H
    -1.02
    xii
    -1.01
    T
    -0.99
     \\
    -0.98
     פֿ
    -0.97
    POSITIVE LOGITS
    龶
    1.35
     péro
    1.33
     تصریح
    1.20
    卨
    1.20
     actrices
    1.15
     花朵
    1.12
    喩
    1.11
     tragé
    1.09
     strategis
    1.09
    ～！
    1.08
    Activations Density 0.024%

    No Known Activations