© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 223121
    Prev
    Next
    INDEX
    Explanations

    calculation and sorting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     methodological
    0.43
     nond
    0.40
     snad
    0.40
    ប្រើ
    0.39
     spes
    0.39
    ⿲
    0.39
    Princeton
    0.37
    gll
    0.37
     throwIfNotFound
    0.37
    #[
    0.37
    POSITIVE LOGITS
    idades
    0.42
     Boogie
    0.42
    étrica
    0.40
     тър
    0.40
    akkhati
    0.40
     интере
    0.39
     interessi
    0.39
    customers
    0.37
     клиентов
    0.37
     сорти
    0.37
    Activations Density 0.000%

    No Known Activations