© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 10820
    Prev
    Next
    INDEX
    Explanations

    property names or fields

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

    the dot operator accessing properties or methods on objects (member access expressions).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron is detecting numeric literal tokens (integers and floats) in code.

    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
     Dinas
    -1.84
    ();*/
    -1.64
     dando
    -1.60
     oef
    -1.57
     THOSE
    -1.53
    蛲
    -1.50
     revered
    -1.48
     unrival
    -1.48
     неделю
    -1.45
    糴
    -1.45
    POSITIVE LOGITS
     a
    1.94
     this
    1.88
     some
    1.67
     subsequently
    1.60
     noticeable
    1.56
     several
    1.52
     consequently
    1.50
     for
    1.50
     using
    1.47
    ・・。
    1.46
    Activations Density 0.012%

    No Known Activations