© 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. 97903
    Prev
    Next
    INDEX
    Explanations

    liber, lib, libre, libyans, liberal

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

    The neuron consistently activates on the character sequence “lib” (e.g. Lib, Liber, liberal, liberated, etc.), i.e. words or tokens containing the “lib” prefix.

    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
    暟
    -0.87
     opportunities
    -0.85
     conductivity
    -0.81
    愷
    -0.77
     probable
    -0.75
    EPI
    -0.75
    postDelayed
    -0.75
     الحل
    -0.75
     our
    -0.74
     modes
    -0.73
    POSITIVE LOGITS
     Lib
    1.19
    liber
    1.05
     lib
    1.03
     LIB
    1.03
     Liber
    1.02
     liber
    0.95
    Lib
    0.94
     Libby
    0.91
    自由
    0.91
    균
    0.91
    Activations Density 0.032%

    No Known Activations