© 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. 53-GEMMASCOPE-2-RES-65K
    7. 3750
    Prev
    Next
    INDEX
    Explanations

    multilingual concepts and places

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

    starts model response title

    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_53_width_65k_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
    p
    0.49
    et
    0.49
    st
    0.47
    ife
    0.47
    z
    0.46
    g
    0.45
    grou
    0.45
    N
    0.45
    ef
    0.44
    за
    0.44
    POSITIVE LOGITS
     अधिकांश
    0.49
    大多數
    0.48
     본격
    0.47
     అమె
    0.47
     எவ்வாறு
    0.46
     বেশির
    0.45
     নিউইয়
    0.45
     বেশিরভাগ
    0.44
    캿
    0.44
     infographic
    0.44
    Activations Density 0.225%

    No Known Activations