© 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. 10-GEMMASCOPE-RES-131K
    7. 84170
    Prev
    Next
    INDEX
    Explanations

    steady state

    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
    apparently
    -2.00
    seems
    -1.88
     to
    -1.84
    玊
    -1.84
    見ても
    -1.80
     Algunos
    -1.78
     who
    -1.73
    various
    -1.67
     The
    -1.66
     recente
    -1.62
    POSITIVE LOGITS
    '
    2.00
     quería
    1.79
     optimal
    1.73
    i
    1.73
    jestel
    1.72
    These
    1.59
    ～～
    1.57
     bidra
    1.55
    計劃
    1.53
     autre
    1.52
    Activations Density 0.021%

    No Known Activations