© 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. 67072
    Prev
    Next
    INDEX
    Explanations

    increasingly

    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
     originally
    -1.77
    และ
    -1.51
     имел
    -1.46
     могат
    -1.43
    zapatos
    -1.42
    aneity
    -1.41
    狴
    -1.41
     márm
    -1.41
     masih
    -1.39
    さは
    -1.38
    POSITIVE LOGITS
    ly
    1.76
    ’
    1.58
    '
    1.46
    an
    1.45
    B
    1.45
    J
    1.43
     increasingly
    1.42
     .
    1.41
    b
    1.41
    ‘
    1.36
    Activations Density 0.028%

    No Known Activations