© 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. 103043
    Prev
    Next
    INDEX
    Explanations

    company president or university

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

    The neuron strongly responds to occurrences of the substring “CAPT”/“CHA” as in the word “CAPTCHA.”

    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
    
    -2.55
     คา
    -2.34
     bluz
    -2.34
    ㍉
    -2.25
    雠
    -2.19
    mädchen
    -2.17
    ⸨
    -2.17
     tissus
    -2.11
     韓
    -2.11
    sieger
    -2.09
    POSITIVE LOGITS
     to
    3.13
     if
    3.02
     in
    2.95
     at
    2.75
     or
    2.69
     for
    2.56
    :
    2.38
    ;
    2.22
     (
    2.19
     /
    2.19
    Activations Density 0.426%

    No Known Activations