© 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. 35280
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

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

    This neuron detects the names of libraries or types (e.g. class/module identifiers) in import or include statements.

    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
    ∫
    -1.04
    ↵↵
    -1.02
    Each
    -1.01
    An
    -0.94
    OF
    -0.93
    ∏
    -0.93
    mtr
    -0.91
    ∑
    -0.90
     each
    -0.89
    ós
    -0.89
    POSITIVE LOGITS
     nedeniyle
    1.19
     positifs
    1.09
     namorados
    1.07
    けどね
    1.07
    Compras
    1.05
    がこの
    1.04
     débris
    1.03
     awakeFromNib
    1.02
     episódios
    1.01
     communs
    1.00
    Activations Density 0.003%

    No Known Activations