© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 6211
    Prev
    Next
    INDEX
    Explanations

    function definitions

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

    This neuron detects code-like tokens and programming identifiers (e.g. method definitions, object attributes, array‐indexing syntax, and file‐path fragments).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    0.55
    for
    0.55
     for
    0.52
    of
    0.49
     Pada
    0.49
     or
    0.47
     Heute
    0.46
    }
    0.44
     The
    0.44
     of
    0.44
    POSITIVE LOGITS
     ajouter
    0.41
    बारक
    0.41
     configur
    0.41
    场景
    0.41
     configure
    0.40
    配置
    0.40
    ल्लिंग
    0.39
    颜值
    0.39
    केंसी
    0.39
    isão
    0.39
    Activations Density 0.003%

    No Known Activations