© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 45238
    Prev
    Next
    INDEX
    Explanations

    geordie shore, Real, Team, Tila, Interleukin, Lenovo

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

    reality TV show names and terms associated with television entertainment programs.

    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
    pC
    -0.86
    existent
    -0.78
    ngulo
    -0.77
    ząt
    -0.77
     jr
    -0.76
     Amalgam
    -0.71
    竝
    -0.71
    ℚ
    -0.70
    csr
    -0.70
     workshops
    -0.68
    POSITIVE LOGITS
    MTV
    1.04
     MTV
    1.03
     吋
    0.78
     STI
    0.73
     Einwohner
    0.73
    Coral
    0.73
     roommates
    0.71
    ᵂ
    0.69
    Flare
    0.69
    Volatile
    0.69
    Activations Density 0.011%

    No Known Activations