© 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. 104554
    Prev
    Next
    INDEX
    Explanations

    cls and clr tokens

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

    This neuron detects occurrences of the three‐letter uppercase acronyms “CLS” or “CLR.”

    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
    我一直
    -2.41
    玧
    -2.28
     搞笑
    -2.28
    𖥧
    -2.19
     новая
    -2.17
     ถ้า
    -2.16
    韪
    -2.13
     Lately
    -2.11
    ↵↵
    -2.09
    玢
    -2.09
    POSITIVE LOGITS
    2
    3.11
    _
    2.77
    냑
    2.55
    of
    2.47
    “
    2.42
    ();
    2.39
    9
    2.34
    也有
    2.34
    at
    2.33
    也
    2.25
    Activations Density 0.001%

    No Known Activations