© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9690
    Prev
    Next
    INDEX
    Explanations

    another kind of file

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

    numbers used in division

    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_40_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
    INT
    0.41
    本文
    0.40
     kè
    0.40
     initComponents
    0.40
    晿
    0.39
     التعريف
    0.38
    Reader
    0.38
    Questo
    0.38
    ...</
    0.38
    ISSN
    0.38
    POSITIVE LOGITS
     fidget
    0.40
    propion
    0.38
    </code>
    0.38
     cenderung
    0.37
     honti
    0.36
     aer
    0.36
    ζί
    0.36
     refinement
    0.36
    होस्
    0.35
    FProperties
    0.35
    Activations Density 0.027%

    No Known Activations