© 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. 22-GEMMASCOPE-RES-131K
    7. 130517
    Prev
    Next
    INDEX
    Explanations

    introduction {#s

    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
    ּוֹ
    -1.27
     исче
    -1.01
    acheter
    -0.95
    べし
    -0.94
     бампер
    -0.93
    וּ
    -0.93
    ayanan
    -0.91
    ̲
    -0.91
     més
    -0.90
    ђа
    -0.88
    POSITIVE LOGITS
     gradually
    1.14
    vances
    1.13
    ׇ
    1.12
     still
    1.11
     masih
    1.07
     slowly
    1.04
     but
    1.04
     ainda
    1.02
     it
    1.00
    段階
    0.99
    Activations Density 0.003%

    No Known Activations