© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70351
    Prev
    Next
    INDEX
    Explanations

    re-compiling

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

    The neuron specifically detects the two‐character ASCII pattern “/\\” (a forward slash immediately followed by a backslash).

    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
    -
    -3.08
    {
    -2.84
     We
    -2.69
     awful
    -2.42
    me
    -2.39
     {
    -2.34
     downright
    -2.31
    を
    -2.30
     ergänzt
    -2.28
     teilweise
    -2.27
    POSITIVE LOGITS
    甃
    2.69
    屨
    2.69
    卝
    2.64
    喾
    2.61
    a
    2.59
    ⮜
    2.55
     ビーチ
    2.52
    卺
    2.48
    ⩴
    2.48
    崋
    2.47
    Activations Density 0.007%

    No Known Activations