© 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. 10-GEMMASCOPE-RES-131K
    7. 43421
    Prev
    Next
    INDEX
    Explanations

    CLDR data, LDML, Reader, xmlrpc, loop

    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
     bricola
    -1.47
     the
    -1.43
     Akhir
    -1.35
     psychiat
    -1.34
     mobilier
    -1.31
     Direktur
    -1.29
     Suiza
    -1.28
     bapt
    -1.27
     完了
    -1.25
     applau
    -1.23
    POSITIVE LOGITS
     """
    1.45
     we
    1.36
    silian
    1.35
     you
    1.34
    <bos>
    1.34
     ,,
    1.33
     поскольку
    1.30
     aVar
    1.28
    volvement
    1.28
     $^{
    1.28
    Activations Density 0.092%

    No Known Activations