© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9
    Prev
    Next
    INDEX
    Explanations

    a followed by description

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

    a followed by descriptor

    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
     。
    0.18
    ↵
    0.17
     which
    0.17
    を使用
    0.17
     denoting
    0.17
     [(
    0.17
     isotherms
    0.17
     $('
    0.17
     或
    0.16
    ().
    0.16
    POSITIVE LOGITS
     realist
    0.16
     действительно
    0.14
     trucker
    0.14
     veritable
    0.14
     multitude
    0.14
     mixtape
    0.13
     pastor
    0.13
     flurry
    0.13
    רי
    0.13
    rizona
    0.13
    Activations Density 1.792%

    No Known Activations