© 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. 10-GEMMASCOPE-RES-131K
    7. 103353
    Prev
    Next
    INDEX
    Explanations

    sm

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

    This neuron detects occurrences of the letter sequence “sm” within individual tokens.

    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
    ↵
    -2.52
    蹀
    -2.34
    ዥ
    -2.33
    轳
    -2.22
    緜
    -2.14
     "");
    -2.13
    鏨
    -2.11
    〤
    -2.08
    乸
    -2.06
    ियन
    -2.02
    POSITIVE LOGITS
    ",
    2.69
    Ꮸ
    2.55
    d
    2.42
    と言って
    2.33
    <
    2.31
    ৢ
    2.27
     solitary
    2.22
    𝐱
    2.17
    謦
    2.16
     fashionable
    2.11
    Activations Density 0.011%

    No Known Activations