© 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. 10-GEMMASCOPE-RES-131K
    7. 102932
    Prev
    Next
    INDEX
    Explanations

    abbreviations like LS

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

    This neuron primarily detects the uppercase token “LS,” especially when it appears as part of an alphanumeric code.

    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
    ཋ
    -3.20
    淠
    -3.08
    蘩
    -2.98
    
    -2.86
    砹
    -2.77
    鷓
    -2.75
    ᕱ
    -2.73
    鵄
    -2.67
    螄
    -2.64
    ～。
    -2.63
    POSITIVE LOGITS
    s
    3.06
    ?"
    2.92
    os
    2.72
    u
    2.50
     loves
    2.50
    j
    2.45
    "
    2.44
    is
    2.44
    ?’
    2.36
     doe
    2.34
    Activations Density 0.006%

    No Known Activations