© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82825
    Prev
    Next
    INDEX
    Explanations

    security headers and protocols

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

    This neuron fires on parts of C/C++ include paths—i.e. folder and file name tokens (especially those with underscores) in `#include` directives.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    retries
    -0.77
     Yad
    -0.72
     tái
    -0.71
    の木
    -0.71
    챕
    -0.69
     Gates
    -0.69
    unsupported
    -0.68
    Mu
    -0.68
     Seller
    -0.67
    時尚
    -0.67
    POSITIVE LOGITS
     Strict
    0.89
     preload
    0.82
     CSP
    0.81
    Strict
    0.78
     Baum
    0.75
    CSP
    0.75
     upgrade
    0.75
     mé
    0.75
     menging
    0.72
     STS
    0.72
    Activations Density 0.022%

    No Known Activations