© 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. 7811
    Prev
    Next
    INDEX
    Explanations

    Vernon Missouri

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

    names, brands, and compound words

    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
    undance
    0.30
    iculture
    0.30
    aide
    0.29
    āk
    0.29
    ừng
    0.29
     အ
    0.28
     chaque
    0.28
    ností
    0.28
    atience
    0.28
    ocity
    0.28
    POSITIVE LOGITS
     biodegradation
    0.33
     pluripotent
    0.29
     "\\
    0.27
     biosynthesis
    0.26
     biodivers
    0.26
    кура
    0.26
     miRNAs
    0.25
    堈
    0.25
     nilpotent
    0.25
     covariates
    0.25
    Activations Density 0.069%

    No Known Activations