© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17227
    Prev
    Next
    INDEX
    Explanations

    park

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

    parks and parsing

    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
    铳
    0.36
    ERATE
    0.35
    multiSelectList
    0.35
    bmatrix
    0.34
    茦
    0.34
    刧
    0.34
     血
    0.34
    墺
    0.34
    scriber
    0.33
     Affiliate
    0.33
    POSITIVE LOGITS
     park
    4.44
    park
    4.09
    Park
    4.00
     парк
    3.98
     PARK
    3.97
     पार्क
    3.95
     پارک
    3.92
     Park
    3.86
     пар
    3.86
     parks
    3.80
    Activations Density 0.378%

    No Known Activations