© 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. 72511
    Prev
    Next
    INDEX
    Explanations

    hyperglycemia treatments or conditions

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

    technical or scientific content that represents separation or boundary indicators.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     опять
    -0.97
    ardecer
    -0.89
     definitivo
    -0.89
     establecidas
    -0.88
     cucharadas
    -0.88
     雞
    -0.87
    apiClient
    -0.84
    isième
    -0.82
    rukt
    -0.81
    hton
    -0.81
    POSITIVE LOGITS
     médec
    1.04
    ַּ
    1.04
     strategis
    0.98
    扩张
    0.95
     armées
    0.93
    っちゃった
    0.92
     蘭
    0.91
     gober
    0.90
    滞在
    0.90
     prefeitura
    0.88
    Activations Density 0.081%

    No Known Activations