© 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. 22-GEMMASCOPE-RES-131K
    7. 70651
    Prev
    Next
    INDEX
    Explanations

    markers followed by context

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

    This neuron detects sequences of hexadecimal digits (bytes or numeric constants) in code or data dumps.

    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
     mikrofon
    -1.20
     kabát
    -1.19
     tesettür
    -1.18
     uſ
    -1.17
     มี
    -1.16
    értel
    -1.16
     rése
    -1.14
    válasz
    -1.14
    orgeous
    -1.14
     majú
    -1.13
    POSITIVE LOGITS
     by
    1.46
     this
    1.34
     those
    1.17
     more
    1.15
     one
    1.13
    .(
    1.13
     both
    1.09
     these
    1.09
     out
    1.06
     ..
    1.06
    Activations Density 0.001%

    No Known Activations