© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58507
    Prev
    Next
    INDEX
    Explanations

    dictionary keys

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

    This neuron activates on references to checking membership in a map (e.g. calls like “contains,” “containsKey,” or “containsValue” on a Map or dictionary).

    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
    lierte
    -0.83
    Ϝ
    -0.73
    igneur
    -0.71
    сезон
    -0.71
    mojo
    -0.71
    rictive
    -0.71
    ಆ
    -0.70
    канал
    -0.69
     kenyataan
    -0.69
    Eksterne
    -0.69
    POSITIVE LOGITS
     keys
    4.88
     key
    3.91
    keys
    3.84
     Keys
    3.55
    Keys
    3.53
    key
    3.05
     клю
    3.03
    Key
    2.95
     Key
    2.94
     getKey
    2.91
    Activations Density 0.094%

    No Known Activations