© 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. 222
    Prev
    Next
    INDEX
    Explanations

    Russian words

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

    Okay, here's the weather

    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
     alleles
    0.41
     puan
    0.36
    ్ఞ
    0.35
    ؤلاء
    0.35
    RxDocument
    0.35
    psies
    0.34
    けど
    0.33
    䒽
    0.33
    可是
    0.33
    んですが
    0.33
    POSITIVE LOGITS
    На
    0.64
    Д
    0.64
    До
    0.63
    За
    0.61
    Па
    0.61
    Об
    0.61
    Пре
    0.59
    Ди
    0.59
    Ста
    0.58
    Про
    0.57
    Activations Density 0.006%

    No Known Activations