© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 188994
    Prev
    Next
    INDEX
    Explanations

    non-english scripts

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

    innovation, future, trends

    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_31_width_262k_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
     sequences
    0.48
    odot
    0.48
    .*?
    0.42
     strategies
    0.42
     unanticipated
    0.42
     unforeseen
    0.41
    urnya
    0.40
     madness
    0.40
     competitively
    0.40
     vocation
    0.39
    POSITIVE LOGITS
    स्टन
    0.46
    开放
    0.45
    س
    0.45
    lichting
    0.45
     Шрифт
    0.44
     Ginkuhà
    0.43
     คะแนน
    0.43
     Calcular
    0.43
     एवरेज
    0.43
    𝐲
    0.43
    Activations Density 0.006%

    No Known Activations