© 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. 8923
    Prev
    Next
    INDEX
    Explanations

    questions and answers

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

    The main thing this neuron does is pick up very common English function words (short high-frequency tokens like “the,” “it,” “was,” “how,” “can,” “to,” “yes,” etc.).

    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
    ꪹ
    -1.87
     they
    -1.83
    鱻
    -1.76
     使っ
    -1.72
     yani
    -1.55
    中です
    -1.53
    紝
    -1.48
    あるので
    -1.45
     сайты
    -1.43
    皝
    -1.42
    POSITIVE LOGITS
    s
    1.99
    /
    1.67
    。
    1.67
    也
    1.67
     In
    1.64
     також
    1.45
    。“
    1.43
    ，
    1.43
    。】
    1.38
    ;
    1.38
    Activations Density 0.020%

    No Known Activations