© 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. 130284
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to rare or nonstandard tokens—especially garbled or unusual unicode characters—within the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    supra shoes, Tag:, Green Line, Q:

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     endi
    -1.28
     nobili
    -1.27
     erit
    -1.27
     morfo
    -1.22
    ñales
    -1.20
     senin
    -1.20
     pantalon
    -1.20
     telepon
    -1.19
     ortop
    -1.18
     padang
    -1.18
    POSITIVE LOGITS
    ϱ
    1.20
     to
    1.20
     größe
    1.17
     "
    1.15
    adoc
    1.14
     dunque
    1.13
     demás
    1.13
     and
    1.09
     generó
    1.05
     BC
    1.04
    Activations Density 0.000%

    No Known Activations