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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2677
    Prev
    Next
    INDEX
    Explanations

    plant parts and species

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

    flowers, trees, and foliage

    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
     كومونز
    0.45
    徹
    0.45
    傌
    0.45
    痞
    0.44
     акты
    0.44
     शिक्
    0.44
     музе
    0.43
    焐
    0.43
    诮
    0.43
    飩
    0.42
    POSITIVE LOGITS
     flowers
    2.14
     shrubs
    2.13
     flowering
    2.09
     foliage
    2.03
     blossoms
    1.98
     shrub
    1.97
     blooms
    1.92
     wildflowers
    1.87
     trees
    1.83
     leaves
    1.76
    Activations Density 0.519%

    No Known Activations