© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34428
    Prev
    Next
    INDEX
    Explanations

    numbers and units

    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_22/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
     enfans
    -1.15
     często
    -1.13
    lichten
    -1.11
     will
    -1.10
     эффективности
    -1.06
     根据
    -1.01
     бампер
    -1.00
     获取
    -0.99
     souvent
    -0.98
     vaak
    -0.98
    POSITIVE LOGITS
     ویتامین
    1.16
    ࿚
    1.12
     Cens
    1.10
    nhung
    1.10
    אַ
    1.08
     سریال
    1.06
     rağmen
    1.04
    readable
    1.04
     Etihad
    1.03
    Vá
    1.02
    Activations Density 0.009%

    No Known Activations