© 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. 73254
    Prev
    Next
    INDEX
    Explanations

    UI code and programming constructs

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

    This neuron fires on programming identifiers—names of functions, classes, constants, flags, etc.

    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
     of
    -1.37
     into
    -1.27
     unggul
    -1.15
    quê
    -1.12
     for
    -1.11
     with
    -1.07
     also
    -1.06
    lustre
    -1.05
    datable
    -1.02
    💞
    -1.01
    POSITIVE LOGITS
     haces
    1.11
     longtime
    1.07
    useless
    1.03
    <bos>
    1.02
    Mó
    1.00
     cuarent
    1.00
    OptionPane
    1.00
    Transk
    0.99
     metabolismo
    0.98
    somewhat
    0.96
    Activations Density 0.027%

    No Known Activations