© 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. 212268
    Prev
    Next
    INDEX
    Explanations

    ", then on

    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
     тільки
    0.41
     попу
    0.41
     entfer
    0.40
    Execute
    0.40
    ombasa
    0.40
     master
    0.39
    asten
    0.39
    ዓ
    0.39
    єм
    0.38
     виконання
    0.38
    POSITIVE LOGITS
     employment
    0.41
     Wage
    0.40
     jobs
    0.40
    क्वल
    0.40
     earnings
    0.39
    走的
    0.39
     assets
    0.38
     ada
    0.38
    Earnings
    0.38
     sinon
    0.37
    Activations Density 0.000%

    No Known Activations