© 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. 65456
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers

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

    This neuron activates on ALL-CAPITAL identifiers or configuration constant names (e.g. environment variable names and other uppercase tokens).

    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
    Джере
    -0.93
     якості
    -0.89
     sytu
    -0.86
    canActivate
    -0.82
    Ответы
    -0.79
    DASH
    -0.79
    Примі
    -0.79
     примі
    -0.78
    Mitä
    -0.78
    regarding
    -0.78
    POSITIVE LOGITS
     UNESCO
    0.82
    奧
    0.82
    krishnan
    0.79
     hereinafter
    0.79
    ✔
    0.78
    ạn
    0.77
     Nilsson
    0.76
    Vs
    0.75
    ước
    0.75
     nodded
    0.74
    Activations Density 0.054%

    No Known Activations