© 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. 8346
    Prev
    Next
    INDEX
    Explanations

    supers or autos prefixes

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

    The neuron detects occurrences of the character sequence “supers” (as in supersaturation, supersymmetric, etc.) in words.

    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
    𓍊
    -2.34
    鲥
    -2.31
     所以
    -2.27
    1
    -2.25
    ſſen
    -2.19
    澌
    -2.19
     模様
    -2.16
     Reſ
    -2.16
     gavetas
    -2.13
     сможет
    -2.11
    POSITIVE LOGITS
    d
    3.08
    </h3>
    3.03
    癀
    2.95
    The
    2.86
    ༈
    2.70
    ࿚
    2.70
    ㉕
    2.61
    "
    2.47
     selben
    2.45
    瑒
    2.44
    Activations Density 0.007%

    No Known Activations