© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113508
    Prev
    Next
    INDEX
    Explanations

    CL followed by common endings

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

    the token "CL" in formal legal and technical documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron specifically detects the uppercase token “CL.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ⡪
    -2.50
    ︐
    -2.39
    猹
    -2.36
    鴬
    -2.34
     Beſ
    -2.28
    ACIONES
    -2.25
     важ
    -2.16
     konsep
    -2.09
     noce
    -2.09
    пь
    -2.08
    POSITIVE LOGITS
    y
    4.03
    ]
    3.13
     differ
    2.88
     появляется
    2.67
     інші
    2.59
    <
    2.58
    CL
    2.44
     οπο
    2.33
    )
    2.33
     этом
    2.31
    Activations Density 0.003%

    No Known Activations