© 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. 91360
    Prev
    Next
    INDEX
    Explanations

    Mercury

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

    four-digit years (like 1965, 2010, etc.) in 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_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
     Lösung
    -0.73
    カプ
    -0.72
    tual
    -0.70
    haping
    -0.69
    ianie
    -0.68
     whales
    -0.67
    hesh
    -0.67
     CFP
    -0.66
    atista
    -0.66
    ussis
    -0.64
    POSITIVE LOGITS
     Hermes
    1.43
    Hermes
    1.37
     Herm
    1.23
    hermes
    1.10
    Herm
    1.04
    Ἑ
    1.00
     hermes
    1.00
     Mercu
    0.94
    kelly
    0.93
     carrés
    0.90
    Activations Density 0.016%

    No Known Activations