© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13563
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite

    OF LIENS RELEASED

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    пр
    0.45
    ской
    0.43
    VERTISING
    0.41
     같아요
    0.41
    ``
    0.40
    īn
    0.40
    olí
    0.40
    หมือน
    0.40
    íž
    0.40
     ``
    0.39
    POSITIVE LOGITS
     modem
    0.65
     Modem
    0.59
    ٠
    0.50
     l
    0.49
     ẞ
    0.47
     f
    0.46
     n
    0.46
     Ln
    0.46
     F
    0.45
     m
    0.45
    Activations Density 0.068%

    No Known Activations