© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48132
    Prev
    Next
    INDEX
    Explanations

    list and string methods

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

    The neuron responds strongly to object attribute or method‐call syntax, i.e. an identifier followed by a dot (`.`).

    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
     last
    -0.94
     Spitz
    -0.73
     Twitter
    -0.68
    कार
    -0.68
     última
    -0.68
     послед
    -0.65
     وست
    -0.65
    last
    -0.64
    Rah
    -0.64
    辰
    -0.64
    POSITIVE LOGITS
    count
    1.31
     count
    1.21
    index
    1.04
     index
    1.00
     counting
    0.90
    pop
    0.88
     Count
    0.88
    .__
    0.87
    counting
    0.86
    Count
    0.85
    Activations Density 0.014%

    No Known Activations