© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12856
    Prev
    Next
    INDEX
    Explanations

    Version, Instrumental, Q, Orlando

    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
     silnika
    -1.31
    쌤
    -1.31
    יסטוריה
    -1.29
    rådet
    -1.24
     امروز
    -1.23
    Халы
    -1.21
     atyp
    -1.16
    yych
    -1.13
     سعر
    -1.13
     unimagin
    -1.12
    POSITIVE LOGITS
     both
    1.63
     from
    1.45
     two
    1.38
     three
    1.38
     after
    1.38
     on
    1.34
     with
    1.32
     by
    1.30
     only
    1.27
     different
    1.22
    Activations Density 0.022%

    No Known Activations