© 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. 2414
    Prev
    Next
    INDEX
    Explanations

    softness and texture

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

    satin

    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
     आक्रोश
    0.43
    ंझ
    0.41
    🌇
    0.41
    സമയം
    0.40
    裨
    0.40
     ታ
    0.40
     कहर
    0.39
    旂
    0.39
     simplification
    0.39
     निवार
    0.39
    POSITIVE LOGITS
     soft
    2.56
     softer
    2.39
     мяг
    2.30
     softness
    2.30
    柔软
    2.30
    soft
    2.25
    柔らか
    2.23
    软
    2.17
     mềm
    2.13
     SOFT
    2.11
    Activations Density 0.520%

    No Known Activations