© 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. 34-GEMMASCOPE-RES-131K
    7. 66148
    Prev
    Next
    INDEX
    Explanations

    java and android imports

    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_34/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
     Ró
    -0.85
     Sekolah
    -0.82
     prof
    -0.82
    Sund
    -0.81
     SUND
    -0.81
    Swi
    -0.79
    aime
    -0.79
     uczniów
    -0.78
    Ideas
    -0.77
     Alphabet
    -0.77
    POSITIVE LOGITS
     however
    0.85
     scheint
    0.78
     vista
    0.78
     systematic
    0.75
     itself
    0.75
    emy
    0.75
    Iterator
    0.73
     enää
    0.73
     also
    0.73
    ाइन
    0.72
    Activations Density 0.009%

    No Known Activations