© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14206
    Prev
    Next
    INDEX
    Explanations

    complete, made, found

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

    cruel were, scenario, later

    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
     thì
    0.30
    as
    0.29
     можна
    0.29
     또는
    0.29
     hoặc
    0.28
    往往
    0.28
    은
    0.28
     त्य
    0.27
    我会
    0.27
     혹은
    0.27
    POSITIVE LOGITS
    。
    0.37
     wobei
    0.32
    ।
    0.30
     recordó
    0.29
     گئی۔
    0.29
     deoarece
    0.28
     கூறினார்
    0.27
     enigmatic
    0.27
    ។
    0.27
     informes
    0.26
    Activations Density 0.009%

    No Known Activations