© 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. 22-GEMMASCOPE-RES-131K
    7. 35602
    Prev
    Next
    INDEX
    Explanations

    NO donor, mechanism sensitivity

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

    references to technical or scientific content in documentation, code, or academic text.

    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
     utilizzata
    -0.98
    ベーション
    -0.85
     and
    -0.80
    bores
    -0.78
    臀
    -0.77
     poiché
    -0.76
     esercit
    -0.76
     drenaje
    -0.76
    Rö
    -0.75
    이며
    -0.75
    POSITIVE LOGITS
     noche
    0.86
    ຫ
    0.85
     Trimble
    0.85
    kript
    0.85
    aside
    0.85
     UTF
    0.82
     КА
    0.82
     McConnell
    0.81
     аниме
    0.81
     Juvenile
    0.79
    Activations Density 0.103%

    No Known Activations