© 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. 116400
    Prev
    Next
    INDEX
    Explanations

    class method overrides

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

    The neuron fires on code‐like structural tokens—things like brackets, braces, quotes, and language keywords (e.g. def, static, function)—i.e. markers of source code syntax.

    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
     ผู้หญิง
    -1.09
    Kullan
    -1.08
     Oyun
    -1.03
    ޓ
    -1.02
     espagne
    -1.02
     Voulez
    -1.00
    Nyt
    -1.00
    getVersion
    -0.99
     preſent
    -0.98
     插图
    -0.96
    POSITIVE LOGITS
    toString
    2.05
     toString
    1.98
     to
    1.91
     equals
    1.87
    ToString
    1.84
     equality
    1.76
     as
    1.54
    equals
    1.53
     comparison
    1.53
    Equals
    1.52
    Activations Density 0.032%

    No Known Activations