© 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. 125
    Prev
    Next
    INDEX
    Explanations

    for followed by purpose or context

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

    for clarity

    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
    in
    0.37
    y
    0.29
     eller
    0.25
    en
    0.25
    es
    0.25
    ed
    0.24
    em
    0.24
    D
    0.23
    O
    0.23
    aç
    0.23
    POSITIVE LOGITS
     sake
    0.24
    ked
    0.22
     purposes
    0.21
     awhile
    0.21
     приобре
    0.20
    giveness
    0.19
    geries
    0.19
     aqueles
    0.19
    творе
    0.19
     целей
    0.19
    Activations Density 0.863%

    No Known Activations