© 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. 112210
    Prev
    Next
    INDEX
    Explanations

    HTTPS, EDTA, requestCode, esModule, ISupport

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

    the term "HTTPS" or similar security/encryption protocol acronyms in technical contexts.

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

    The neuron responds to abbreviations or acronyms—especially sequences of uppercase letters (e.g. “HTTPS,” “SSL,” “EDTA”).

    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
    '
    -3.50
    —
    -2.81
    ;
    -2.73
    -2.69
    “
    -2.52
    }
    -2.45
    %
    -2.38
    o
    -2.34
     
    -2.31
    s
    -2.22
    POSITIVE LOGITS
    
    2.81
    戗
    2.61
    檍
    2.56
     موب
    2.55
    Ꭳ
    2.53
    鸱
    2.52
    谡
    2.48
    艫
    2.44
    ﹍﹍
    2.42
    
    2.42
    Activations Density 0.001%
    No Known Activations