© 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. 22-GEMMASCOPE-RES-131K
    7. 128327
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily detects long sequences of digits (numeric identifiers or codes).

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

    web links and multilingual content

    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
    Ƅ
    -1.01
     nothing
    -0.99
    mcc
    -0.94
    illiers
    -0.92
    国的
    -0.92
     again
    -0.90
     his
    -0.90
     unſ
    -0.89
     vegetables
    -0.88
     nzuri
    -0.87
    POSITIVE LOGITS
     Mereka
    1.09
    remos
    0.99
    当時
    0.96
     jejich
    0.93
    了过来
    0.93
    了出来
    0.91
     několika
    0.90
    Мон
    0.90
    Čo
    0.90
     Phần
    0.90
    Activations Density 0.023%

    No Known Activations