© 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. 14820
    Prev
    Next
    INDEX
    Explanations

    you know

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

    you know

    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
    шем
    0.46
     szá
    0.45
     dî
    0.45
     gezogen
    0.43
    隗
    0.42
     знаний
    0.42
     یقینی
    0.41
     xiii
    0.41
     acknow
    0.41
     protezione
    0.41
    POSITIVE LOGITS
    General
    0.46
    Creo
    0.45
    ת
    0.45
    Big
    0.44
    ?
    0.44
    ING
    0.43
    YAN
    0.43
    Ketika
    0.43
     rumors
    0.42
    Truth
    0.42
    Activations Density 0.081%

    No Known Activations