© 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. 36123
    Prev
    Next
    INDEX
    Explanations

    ported, free, sent, gift, coins, came

    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
    ただし
    -1.09
     most
    -1.08
     now
    -1.06
     from
    -1.06
     we
    -1.05
     تحقق
    -1.03
     every
    -0.98
     will
    -0.98
    begin
    -0.97
     or
    -0.97
    POSITIVE LOGITS
     Цвет
    1.27
     supuestamente
    1.20
     Estaba
    1.18
     وكان
    1.11
    なのに
    1.11
    ⩥
    1.09
    Tarih
    1.07
     pourtant
    1.07
    supposed
    1.06
     Simplemente
    1.05
    Activations Density 0.017%

    No Known Activations