© 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. 71225
    Prev
    Next
    INDEX
    Explanations

    finding index and next

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

    The neuron is keyed to detect camel-case code identifiers (e.g. method or variable names like containsObject, indexOfObject, 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
     świąte
    -0.90
    Thêm
    -0.82
     соединения
    -0.77
    terape
    -0.77
     hereafter
    -0.73
     later
    -0.73
     réve
    -0.72
     heterogeneity
    -0.72
     nový
    -0.71
    aktor
    -0.71
    POSITIVE LOGITS
     getIndex
    0.85
     brack
    0.84
    IndexOf
    0.83
     reprez
    0.83
     причи
    0.82
     indexOf
    0.78
     иден
    0.78
     corresponding
    0.77
     Hamm
    0.77
     getSource
    0.76
    Activations Density 0.026%

    No Known Activations