© 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. 34-GEMMASCOPE-RES-131K
    7. 91667
    Prev
    Next
    INDEX
    Explanations

    ids, database columns

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

    This neuron fires on code identifiers and syntax tokens involving underscores or dot separators (e.g., variable or table names with “_” or “.”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    readyState
    -0.81
    нан
    -0.79
    fers
    -0.79
    挛
    -0.77
    跚
    -0.76
    лек
    -0.71
    ñones
    -0.71
    bridi
    -0.71
    sendKeys
    -0.71
    okości
    -0.71
    POSITIVE LOGITS
    ランダ
    0.90
     master
    0.85
     Masters
    0.84
     poquito
    0.84
     intervento
    0.83
     module
    0.81
    睑
    0.80
     trash
    0.79
    Mst
    0.78
    Carolyn
    0.78
    Activations Density 0.007%

    No Known Activations