© 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. 10-GEMMASCOPE-RES-131K
    7. 8082
    Prev
    Next
    INDEX
    Explanations

    code loops

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

    This neuron detects method calls that retrieve the length or size of a data structure (e.g. “.size()”, “.Length()”).

    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
     for
    -2.31
    穑
    -1.98
     has
    -1.95
     or
    -1.93
     arī
    -1.84
     což
    -1.83
    蠖
    -1.78
    嶮
    -1.70
     ktoré
    -1.70
    França
    -1.68
    POSITIVE LOGITS
    The
    2.84
    _
    2.80
    7
    2.16
    It
    2.13
    (
    2.08
    許多
    1.99
    8
    1.98
    For
    1.93
    4
    1.92
    -
    1.91
    Activations Density 0.001%

    No Known Activations