© 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. 22-GEMMASCOPE-RES-131K
    7. 26600
    Prev
    Next
    INDEX
    Explanations

    paired concepts or antonyms

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

    This neuron is essentially inactive—it does not reliably respond to any token.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     花纹
    -2.03
     复古
    -2.02
     花朵
    -1.87
    här
    -1.84
     新款
    -1.81
     抠
    -1.79
     vixion
    -1.74
     菇
    -1.73
     både
    -1.73
    鶺
    -1.72
    POSITIVE LOGITS
    J
    1.96
     also
    1.92
    P
    1.87
    F
    1.84
    T
    1.84
    M
    1.84
    Y
    1.83
    R
    1.81
    E
    1.81
     J
    1.81
    Activations Density 0.019%

    No Known Activations