© 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. 2451
    Prev
    Next
    INDEX
    Explanations

    generated javadoc comments

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

    This neuron detects references to base-64 encoding (e.g. “base64” imports or function calls).

    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
     ppm
    -0.79
     nemoc
    -0.78
     TextStyle
    -0.77
     Diabetic
    -0.75
    لمين
    -0.75
     Mineral
    -0.75
    颜
    -0.74
    diagnos
    -0.73
     Bitmap
    -0.72
     insulin
    -0.71
    POSITIVE LOGITS
    ongeza
    0.87
    白
    0.74
     urls
    0.74
    urz
    0.73
    urls
    0.71
    贝
    0.71
     Panda
    0.70
    Sorry
    0.69
     Dewey
    0.69
     envelop
    0.69
    Activations Density 0.008%

    No Known Activations