© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66565
    Prev
    Next
    INDEX
    Explanations

    programming and natural language

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

    This neuron detects C# attribute declarations inside square brackets (e.g. [ValidateInput(false)]).

    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
     Verkäufer
    -1.27
     zaczyna
    -1.13
     начала
    -1.05
    rania
    -1.02
    															
    -1.01
     vilá
    -1.00
     ríos
    -0.99
     Soporte
    -0.98
    机会
    -0.97
     Käufer
    -0.96
    POSITIVE LOGITS
     AMEN
    1.06
    Presenters
    0.97
    Continu
    0.93
     and
    0.92
    TEMPO
    0.89
    fde
    0.88
     chibi
    0.86
     оконча
    0.86
     homie
    0.85
    ญี่ป
    0.84
    Activations Density 0.001%

    No Known Activations