© 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. 10622
    Prev
    Next
    INDEX
    Explanations

    source or means for something

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

    essential support or starting point

    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
     وليس
    0.45
    volving
    0.44
     кров
    0.43
     physiologically
    0.41
     functionally
    0.41
    edly
    0.40
    缺
    0.40
    䀎
    0.39
     dotyczą
    0.38
     developmentally
    0.38
    POSITIVE LOGITS
     многочис
    0.45
    ことから
    0.43
    ట్టు
    0.42
     новых
    0.40
    Jenny
    0.40
     zahlreichen
    0.39
     новую
    0.39
    जरीवाल
    0.39
     Provided
    0.38
     yerde
    0.38
    Activations Density 0.104%

    No Known Activations