© 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. 22-GEMMASCOPE-RES-131K
    7. 65297
    Prev
    Next
    INDEX
    Explanations

    `.` and programming terms

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

    The neuron is primarily detecting the forward‐slash character “/” whenever it appears.

    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
     RECOMEND
    -1.02
     MÁS
    -0.96
     coreana
    -0.95
     Jehová
    -0.94
    cemic
    -0.94
     Vietnam
    -0.93
     cubana
    -0.92
    ‣
    -0.90
     offerts
    -0.89
    悍
    -0.88
    POSITIVE LOGITS
     汽车
    1.09
    éte
    1.01
     क्यों
    1.01
     incursion
    0.94
     Nhưng
    0.93
     exis
    0.90
    Ikke
    0.90
    書く
    0.88
     envo
    0.88
    eaking
    0.87
    Activations Density 0.055%

    No Known Activations