© 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. 10-GEMMASCOPE-RES-131K
    7. 66120
    Prev
    Next
    INDEX
    Explanations

    planned future events

    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
    ⡪
    -1.53
     umano
    -1.51
    férence
    -1.37
    when
    -1.36
    ＝＝
    -1.35
     scoperto
    -1.35
     pilota
    -1.34
    Its
    -1.33
     появля
    -1.32
     zustand
    -1.30
    POSITIVE LOGITS
     =
    1.73
     for
    1.56
    ünden
    1.48
     také
    1.47
     Révolution
    1.43
    ↵↵↵
    1.41
    ulico
    1.39
    </h5>
    1.38
     '
    1.33
    ıcı
    1.32
    Activations Density 0.045%

    No Known Activations