© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10420
    Prev
    Next
    INDEX
    Explanations

    array indexing and assignment

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

    array indexing or properties

    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
    酝
    0.40
    Ἔ
    0.40
    которые
    0.39
     Müdür
    0.39
     কন্যার
    0.38
    계를
    0.38
    ابعه
    0.37
    数を
    0.37
    彼の
    0.37
    issory
    0.37
    POSITIVE LOGITS
     *(
    0.64
    第
    0.58
    *(
    0.57
     objectAtIndex
    0.56
    ByIndex
    0.54
    (*(
    0.52
    tenth
    0.51
    _[
    0.50
    AtIndex
    0.50
    第九
    0.50
    Activations Density 0.032%

    No Known Activations