© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4304
    Prev
    Next
    INDEX
    Explanations

    connectors and punctuation

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

    Mistral

    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
    த்திற்கும்
    0.43
    Vamos
    0.41
    ﺌ
    0.41
    liness
    0.40
     Temos
    0.40
     Imágenes
    0.40
    Artículo
    0.39
    ・
    0.39
    mans
    0.39
    ను
    0.39
    POSITIVE LOGITS
    在于
    0.49
    其
    0.47
    因为
    0.46
    在其
    0.45
    它是
    0.44
    ếu
    0.43
    上述
    0.43
    無論
    0.43
    实现了
    0.43
     owing
    0.41
    Activations Density 0.003%

    No Known Activations