© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11124
    Prev
    Next
    INDEX
    Explanations

    web resource inclusion

    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
     this
    -2.08
     to
    -1.60
     for
    -1.48
     all
    -1.45
     from
    -1.38
    a
    -1.17
    ForResult
    -1.13
     each
    -1.11
     if
    -1.10
     just
    -1.09
    POSITIVE LOGITS
    Recept
    1.45
    توضیحات
    1.34
    Texte
    1.33
    Médaille
    1.33
    Tür
    1.29
    Doktor
    1.28
    Komentar
    1.27
     secado
    1.27
    Kontra
    1.26
    Liet
    1.25
    Activations Density 0.009%

    No Known Activations