© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8683
    Prev
    Next
    INDEX
    Explanations

    sl slaus slav slugh slaver slowness slinky

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

    slow / sl prefixes

    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_40_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
    诉
    0.43
     CFU
    0.41
     Pflanzen
    0.40
    的
    0.39
     Jacq
    0.38
    ismuth
    0.38
    ruth
    0.38
     Pä
    0.37
    esi
    0.37
    bsen
    0.37
    POSITIVE LOGITS
     슬
    0.94
     sl
    0.91
     Sl
    0.88
    Sl
    0.82
     slur
    0.80
     SL
    0.78
     Сла
    0.74
     স্ল
    0.73
     slap
    0.73
    슬
    0.72
    Activations Density 0.086%

    No Known Activations