© 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. 23680
    Prev
    Next
    INDEX
    Explanations

    typeof homepage illustrated

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     источников
    -0.83
    aad
    -0.74
     deliberately
    -0.73
     bewust
    -0.73
    特性
    -0.71
     visibility
    -0.71
     yesterday
    -0.71
    tés
    -0.70
     intentionally
    -0.70
    src
    -0.69
    POSITIVE LOGITS
    豁
    0.87
    RLock
    0.81
    rige
    0.76
    PPE
    0.75
    CDMA
    0.74
    🕉
    0.73
    🪔
    0.72
    DCS
    0.72
    olini
    0.72
    Corre
    0.71
    Activations Density 0.060%

    No Known Activations