© 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. 10994
    Prev
    Next
    INDEX
    Explanations

    a given

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

    a number, variable, or feature

    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
    eben
    0.38
     metallurgy
    0.37
     ユ
    0.37
    രായ
    0.37
     tű
    0.36
     Yukon
    0.36
    ով
    0.35
    :&
    0.35
     représentants
    0.35
     Adası
    0.34
    POSITIVE LOGITS
     particular
    0.86
    particular
    0.81
     given
    0.81
    given
    0.75
     particulière
    0.67
     particulares
    0.67
     particolare
    0.66
    Particular
    0.64
     Particular
    0.63
    给定
    0.63
    Activations Density 0.223%

    No Known Activations