© 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. 27817
    Prev
    Next
    INDEX
    Explanations

    each noun

    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
     very
    -1.27
    ありますが
    -1.17
     something
    -1.11
    b
    -1.09
    ことも
    -1.07
    Grafik
    -1.04
    ものを
    -1.02
    ところに
    -1.02
    某个
    -1.02
    しば
    -1.02
    POSITIVE LOGITS
    が
    1.47
     that
    1.45
     separately
    1.35
     réglementation
    1.32
     of
    1.32
     einzeln
    1.30
     Ogni
    1.30
     individually
    1.29
     каждого
    1.29
    <bos>
    1.28
    Activations Density 0.064%

    No Known Activations