© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14886
    Prev
    Next
    INDEX
    Explanations

    compilers support

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

    This neuron detects technical terms and tokens that specify computing platforms, compilers, versions, or compatibility directives.

    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
     Feuchtigkeit
    -1.01
     molho
    -1.00
     raccont
    -0.99
     μὲν
    -0.95
     last
    -0.94
    opie
    -0.94
    aikan
    -0.93
     выгод
    -0.91
     Tonnen
    -0.91
     the
    -0.91
    POSITIVE LOGITS
     where
    1.09
     onwards
    1.09
     отличаются
    1.04
    両方
    1.00
    Ʋ
    0.96
    ◀
    0.94
    يست
    0.93
     där
    0.93
     муніципалі
    0.93
     Résultat
    0.92
    Activations Density 0.144%

    No Known Activations