© 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. 31-GEMMASCOPE-2-RES-262K
    7. 176104
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    imperative mood and numerical values

    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_262k_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
    manın
    0.52
     unavailability
    0.48
     බැ
    0.46
     lizard
    0.46
     accustomed
    0.46
     verwend
    0.46
     និង
    0.46
    ;
    0.46
     Verw
    0.46
    ಂಗ್
    0.45
    POSITIVE LOGITS
    人で
    0.52
    柢
    0.43
    Whitelist
    0.41
    Ё
    0.41
    TL
    0.41
    屹
    0.40
    最大
    0.40
    Dr
    0.40
     странице
    0.40
    上で
    0.40
    Activations Density 0.001%

    No Known Activations