© 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. 26512
    Prev
    Next
    INDEX
    Explanations

    date and code structures

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

    This neuron activates on programmer-defined identifiers (variable names, type parameters, and other user-defined symbols) rather than keywords or punctuation.

    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
     adecuadas
    -1.08
     maquiagem
    -1.05
    ldquo
    -1.01
    だと思います
    -0.99
     your
    -0.99
     yourself
    -0.98
     jazdy
    -0.97
     verzorg
    -0.96
    medskip
    -0.94
     Yourself
    -0.93
    POSITIVE LOGITS
    もありますが
    1.09
    并非
    1.03
    せっかく
    1.02
    曲は
    1.02
    もありました
    0.97
     puisque
    0.97
     каже
    0.96
     стане
    0.95
     насос
    0.94
     in
    0.92
    Activations Density 0.001%

    No Known Activations