© 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. 22-GEMMASCOPE-RES-131K
    7. 27501
    Prev
    Next
    INDEX
    Explanations

    code imports and calls

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

    The neuron is detecting dotted identifier chains (object or module names followed by “.” and an attribute or method name) 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_22/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
    って思
    -1.92
     in
    -1.77
    ですが
    -1.73
    UCIÓN
    -1.72
     سایر
    -1.68
     rique
    -1.66
     berbagai
    -1.66
     nyní
    -1.65
    などが
    -1.63
    だからこそ
    -1.62
    POSITIVE LOGITS
    .
    2.25
    ,
    1.88
    “
    1.79
    久しぶり
    1.58
    久し
    1.56
     seront
    1.53
    を行い
    1.50
    -
    1.47
    3
    1.46
     eene
    1.45
    Activations Density 0.008%

    No Known Activations