© 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. 10939
    Prev
    Next
    INDEX
    Explanations

    start of phrases, questions, or code

    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
     всегда
    -1.24
    sekret
    -1.09
     também
    -1.05
    álny
    -1.02
     maleta
    -1.02
    couts
    -1.02
     setiap
    -1.00
     desmotiv
    -1.00
     desperdic
    -0.99
    seamnă
    -0.99
    POSITIVE LOGITS
     to
    1.42
    cen
    1.07
    Zwei
    1.05
    ⅖
    0.99
     =>'
    0.96
    ce
    0.92
    #'
    0.91
    /*
    0.90
    ⵉ
    0.90
     чрезвы
    0.89
    Activations Density 0.001%

    No Known Activations