© 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. 10-GEMMASCOPE-RES-131K
    7. 19091
    Prev
    Next
    INDEX
    Explanations

    copyright notices

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

    The neuron detects the opening delimiter of C-style block comments (i.e. “/*”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    翃
    -2.66
    !"
    -2.39
     แต่
    -2.38
    u
    -2.27
    паковка
    -2.23
    籏
    -2.23
    ()"
    -2.22
    踽
    -2.19
    )("
    -2.16
    ”？
    -2.14
    POSITIVE LOGITS
    1
    3.31
    تیجه
    3.22
    The
    3.22
    9
    2.95
    4
    2.80
    6
    2.75
    In
    2.69
    0
    2.66
    Also
    2.64
    7
    2.63
    Activations Density 0.000%

    No Known Activations