© 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. 76154
    Prev
    Next
    INDEX
    Explanations

    essential medium

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

    terms related to scientific or legal media and publications, particularly names of media/journals, court documents, and scientific culture media.

    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_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
    ̯
    -0.71
    колай
    -0.69
     hooded
    -0.66
    쥬
    -0.65
     Krak
    -0.65
    Sys
    -0.65
     premises
    -0.65
     仮面
    -0.63
    <!--<
    -0.63
     ਵ
    -0.63
    POSITIVE LOGITS
    Bases
    0.76
    귀
    0.66
     revolutions
    0.65
    hø
    0.64
    batis
    0.63
    jai
    0.62
     base
    0.61
     Observing
    0.61
     Eagle
    0.61
     bases
    0.61
    Activations Density 0.094%

    No Known Activations