© 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. 22-GEMMASCOPE-RES-131K
    7. 27253
    Prev
    Next
    INDEX
    Explanations

    technical headings and code prefixes

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

    The neuron strongly activates on forward‐slash tokens, i.e. the “/” characters used as path or file separators.

    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
    不断的
    -1.00
    𝗬
    -0.99
    ismes
    -0.98
     kérdés
    -0.93
    可以让
    -0.90
    芩
    -0.88
    freude
    -0.88
     consentimento
    -0.87
     adım
    -0.87
    uellement
    -0.87
    POSITIVE LOGITS
     new
    1.06
    檗
    1.02
     rantai
    1.00
     NEVER
    0.91
     nuevos
    0.90
    ResponseStatus
    0.90
    していて
    0.88
     norte
    0.85
     членов
    0.85
     menurun
    0.82
    Activations Density 0.000%

    No Known Activations