© 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. 1278
    Prev
    Next
    INDEX
    Explanations

    ขึ้นอยู่กับ

    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
    ویزی
    0.45
    伐
    0.42
     പോലീസ്
    0.42
     atha
    0.39
    िश्वत
    0.38
     Pickett
    0.38
    పోయే
    0.38
    SSFWorkbook
    0.38
     ikat
    0.38
     दस्ता
    0.37
    POSITIVE LOGITS
    斷
    0.40
     Determined
    0.40
    determined
    0.39
    hene
    0.38
     biens
    0.37
    stood
    0.37
     determined
    0.37
     cheek
    0.36
     flushed
    0.36
     રચ
    0.36
    Activations Density 0.000%

    No Known Activations