© 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. 17519
    Prev
    Next
    INDEX
    Explanations

    interior design and decorating

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

    interior decorating

    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
     opportunistic
    0.55
     lubric
    0.44
    Opportun
    0.43
     probing
    0.42
     grizz
    0.42
    шымта
    0.42
     Opportun
    0.41
    燧
    0.41
     intraper
    0.40
     ambulances
    0.40
    POSITIVE LOGITS
     interior
    2.20
     Interior
    2.17
     decorating
    2.17
     interiors
    2.16
    Interior
    2.14
    interior
    2.13
     decorator
    2.03
    インテリア
    2.02
     Interiors
    2.00
     Decor
    1.99
    Activations Density 0.536%

    No Known Activations