© 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. 15646
    Prev
    Next
    INDEX
    Explanations

    different languages or prefixes

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

    multilingual content

    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
    此外
    0.29
     protagonisti
    0.28
     ところ
    0.27
     svojoj
    0.27
    ))$.
    0.26
    stopPropagation
    0.26
     diverg
    0.26
    н
    0.26
     anos
    0.26
    ꫝ
    0.26
    POSITIVE LOGITS
    ائی
    0.29
    AIS
    0.28
     আপনাকে
    0.28
    ాత్రి
    0.28
    ائ
    0.28
     Dealers
    0.28
    ävät
    0.28
     بچه
    0.27
     все
    0.27
    Analytics
    0.27
    Activations Density 0.024%

    No Known Activations