© 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. 9748
    Prev
    Next
    INDEX
    Explanations

    initial letters followed by completions

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

    technical acronyms or identifiers

    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
    oft
    0.59
    gelopen
    0.55
    تها
    0.54
    aver
    0.51
    aa
    0.49
    هُ
    0.49
    saw
    0.49
    oque
    0.49
    t
    0.48
    sman
    0.48
    POSITIVE LOGITS
     diffé
    0.47
     doom
    0.47
     revêt
    0.46
    Nz
    0.45
    rosi
    0.45
     bienvenue
    0.44
     НА
    0.44
    OutOf
    0.44
    VariableName
    0.44
     lắm
    0.43
    Activations Density 1.141%

    No Known Activations