© 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. 33675
    Prev
    Next
    INDEX
    Explanations

    Preliminary studies; Il Divo; mutation of

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

    formatting or syntax elements in code, documentation, and technical files.

    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
     gani
    -1.09
    moja
    -0.93
     mahu
    -0.89
     and
    -0.85
     yako
    -0.84
    Gilla
    -0.84
    เหรียญ
    -0.84
     publiek
    -0.83
    ówczas
    -0.83
    امکان
    -0.83
    POSITIVE LOGITS
     something
    1.18
    ，“
    1.16
    (#
    1.02
    inz
    1.02
     обычно
    1.01
    (/
    1.00
     superstar
    0.99
     inimes
    0.99
    ______
    0.99
     awesome
    0.98
    Activations Density 0.000%

    No Known Activations