© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40724
    Prev
    Next
    INDEX
    Explanations

    No **** Sherlock, you posted

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    vantaged
    -3.08
    瑒
    -2.80
     expérience
    -2.44
    嫫
    -2.39
     <>",
    -2.38
    沇
    -2.38
    銼
    -2.36
    AutoresizingMask
    -2.34
    呜呜
    -2.33
    呦
    -2.31
    POSITIVE LOGITS
    ’
    2.97
    但
    2.80
     cette
    2.42
    to
    2.36
    2.33
     semplici
    2.30
    但我
    2.20
     această
    2.14
    這個
    2.13
    ?”
    2.11
    Activations Density 0.002%

    No Known Activations