© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 9
    Prev
    Next
    INDEX
    Explanations

    financial and transactional terms

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

    creative text formats

    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
    &
    0.55
    And
    0.46
    และ
    0.45
     하고
    0.44
    &&\
    0.43
     १२
    0.43
    是一个
    0.42
    HTTPSampler
    0.42
     &_
    0.41
    แล
    0.41
    POSITIVE LOGITS
    조
    0.42
    よう
    0.36
    ersi
    0.35
     sout
    0.34
     potřeb
    0.34
    ))^{
    0.34
     よう
    0.33
     quince
    0.33
    ন্তু
    0.33
    ost
    0.32
    Activations Density 0.165%

    No Known Activations