© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129040
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and indices

    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
     Darüber
    -0.88
     અને
    -0.87
     pihaknya
    -0.87
     Inoltre
    -0.87
    Jawaban
    -0.85
    そして
    -0.85
    3
    -0.85
     Aufgrund
    -0.84
     jejich
    -0.84
     Mentre
    -0.84
    POSITIVE LOGITS
     nélk
    1.04
     manualidades
    1.01
     Rings
    0.99
    ());
    0.98
     cortas
    0.95
     hicimos
    0.95
    mvh
    0.94
     chistes
    0.94
    chemise
    0.94
    リヤ
    0.93
    Activations Density 0.009%

    No Known Activations