© 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. 308
    Prev
    Next
    INDEX
    Explanations

    Russian Cyrillic letters

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

    markdown list formatting

    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
    ᱼ
    0.40
     perangkat
    0.34
    私募基金
    0.33
    Genes
    0.32
     â
    0.32
     coches
    0.32
    ktCap
    0.32
    ديث
    0.32
    クロマト
    0.32
     খুবই
    0.32
    POSITIVE LOGITS
    М
    0.63
    У
    0.61
    Б
    0.58
    Д
    0.54
    П
    0.54
    Ма
    0.52
    К
    0.52
    А
    0.49
    До
    0.49
    В
    0.47
    Activations Density 0.399%

    No Known Activations