© 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. 34434
    Prev
    Next
    INDEX
    Explanations

    programming data types

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

    The neuron flags programming language type names (e.g. int, float, bool, string, Dictionary, 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
     damaligen
    -1.16
     then
    -1.11
    Kenapa
    -1.06
     damals
    -1.02
    Not
    -0.97
    当时
    -0.96
     fellow
    -0.95
    當時
    -0.94
    当年
    -0.93
     wahrscheinlich
    -0.93
    POSITIVE LOGITS
    disposing
    1.20
     található
    1.20
    ecl
    1.16
    вку
    1.14
    хта
    1.09
    琑
    1.05
     can
    1.03
     négy
    1.02
     május
    1.01
     uttry
    1.01
    Activations Density 0.049%

    No Known Activations