© 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. 34-GEMMASCOPE-RES-131K
    7. 57856
    Prev
    Next
    INDEX
    Explanations

    certificate and security exceptions

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

    This neuron strongly responds to uppercase identifiers and labels—things like C/C++ preprocessor macro names or multi‐word titles written in all capitals.

    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
    SEN
    -0.73
    ONT
    -0.71
    Compat
    -0.71
    glia
    -0.71
    rippa
    -0.69
    collection
    -0.69
    oló
    -0.68
     uzyskać
    -0.68
    fen
    -0.67
    hide
    -0.66
    POSITIVE LOGITS
     exceptions
    0.72
    wanan
    0.71
    alisasi
    0.71
     solicitors
    0.71
    origins
    0.70
    𝗕
    0.70
    zanie
    0.68
     avocat
    0.68
    
    0.68
     уровень
    0.68
    Activations Density 0.039%

    No Known Activations