© 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. 34-GEMMASCOPE-RES-131K
    7. 65642
    Prev
    Next
    INDEX
    Explanations

    unknown or unrecognized

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

    This neuron detects references to catch-all or fallback URL routing patterns (e.g. “any unmatched url”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    avor
    -0.85
     BECAUSE
    -0.80
    gup
    -0.80
    cys
    -0.79
     Estadística
    -0.78
     места
    -0.77
    lili
    -0.77
    fie
    -0.76
     två
    -0.76
    NullException
    -0.76
    POSITIVE LOGITS
     unknown
    3.63
    Unknown
    3.20
    unknown
    3.03
     Unknown
    2.97
     неизвест
    2.52
    UNKNOWN
    2.48
     unrecognized
    2.41
     UNKNOWN
    2.31
     unknowns
    2.19
     desconocido
    2.11
    Activations Density 0.027%

    No Known Activations