© 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. 10-GEMMASCOPE-RES-131K
    7. 19525
    Prev
    Next
    INDEX
    Explanations

    future Hall

    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
     kurios
    -2.14
     bija
    -2.06
     أنها
    -2.00
    wendige
    -1.89
     unhelpful
    -1.88
     menak
    -1.88
    ☆☆
    -1.86
    ⃙
    -1.86
    🍄
    -1.79
     Theres
    -1.78
    POSITIVE LOGITS
    3
    2.64
    i
    2.38
    (
    2.25
    u
    2.22
    to
    2.16
    al
    2.14
    2
    2.02
    $
    2.02
    an
    2.00
    c
    2.00
    Activations Density 0.001%

    No Known Activations