© 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. 1710
    Prev
    Next
    INDEX
    Explanations

    color accents textural details

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

    bright, muted colors

    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
     whereupon
    0.43
     unprofitable
    0.41
     कानूनों
    0.41
     जुगा
    0.41
     काबिल
    0.40
     engend
    0.39
    🏪
    0.39
    엌
    0.39
     inconven
    0.39
    公平
    0.39
    POSITIVE LOGITS
     subtle
    1.24
     textured
    1.22
     muted
    1.19
     contrasting
    1.16
     pastel
    1.13
     metallic
    1.09
     textures
    1.09
     texture
    1.06
     accents
    1.05
     textural
    1.05
    Activations Density 1.075%

    No Known Activations