© 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. 68877
    Prev
    Next
    INDEX
    Explanations

    names followed by exclamations

    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
    nossa
    -1.01
     or
    -0.99
     leider
    -0.99
    ditions
    -0.97
     the
    -0.96
    quién
    -0.96
    茎
    -0.93
     Дата
    -0.93
    ものである
    -0.92
    ᑐ
    -0.92
    POSITIVE LOGITS
    !
    1.94
    !!
    1.31
    !"
    1.20
     you
    1.19
    !
    
    1.18
    !!!
    1.13
    !
    1.11
    基本的に
    1.07
     můžete
    1.07
    !)
    1.07
    Activations Density 0.009%

    No Known Activations