© 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-16K
    7. 12401
    Prev
    Next
    INDEX
    Explanations

    commercial trade and magic

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

    need to

    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
     PrintWriter
    0.53
    RE
    0.52
    ASCII
    0.51
     ASCII
    0.50
    ê
    0.47
     FILES
    0.46
    :
    0.46
     Files
    0.46
    _
    0.46
     номе
    0.45
    POSITIVE LOGITS
    罚
    0.51
    骖
    0.49
    charg
    0.46
    ږد
    0.45
    نګه
    0.45
    Однако
    0.44
     incentiv
    0.43
    ،
    0.43
    कारात्मक
    0.43
     एक्चु
    0.43
    Activations Density 0.001%

    No Known Activations