© 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. 130085
    Prev
    Next
    INDEX
    Explanations

    The neuron flags tokens written in non-Latin scripts or otherwise containing non-English Unicode characters.

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

    倒序, 正序, 版本, 当日

    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
    乆
    -2.88
    vantaged
    -2.84
    
    -2.66
     natür
    -2.38
    拥抱
    -2.34
    ほか
    -2.33
    ឵
    -2.30
     selben
    -2.30
     Таким
    -2.25
     This
    -2.17
    POSITIVE LOGITS
    $
    2.31
    '
    2.25
    檍
    2.23
     itſelf
    2.22
     russo
    2.22
     ".";
    2.13
    垆
    2.08
    вні
    2.03
     ragaz
    2.03
     ".",
    2.00
    Activations Density 0.002%

    No Known Activations