© 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. 12548
    Prev
    Next
    INDEX
    Explanations

    stone, well, please, swimming, requires, thanks

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

    quotation marks and dashes

    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
    '
    0.64
     Votre
    0.52
     Birmingham
    0.48
     turtleneck
    0.48
     США
    0.46
     sarà
    0.46
     Billy
    0.46
     มัน
    0.45
    今天要
    0.43
     Alps
    0.43
    POSITIVE LOGITS
    та
    0.68
    માં
    0.62
    ް
    0.61
    িক
    0.59
    1
    0.59
    وك
    0.58
    oksi
    0.58
     unintentionally
    0.58
     chết
    0.56
     mua
    0.55
    Activations Density 0.264%

    No Known Activations