© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 1739
    Prev
    Next
    INDEX
    Explanations

    specific compound phrases

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

    AI, CNN, Fight, Procedures, Web, filtering

    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
     ஆகியோர்
    0.39
     आदी
    0.36
     農
    0.36
    ⣀
    0.34
     patip
    0.34
    èng
    0.33
     nhá
    0.33
     እነዚህ
    0.33
     நடந்த
    0.32
     âgé
    0.32
    POSITIVE LOGITS
    ——
    0.34
    ления
    0.31
    ዋ
    0.31
    ฀
    0.31
     ●
    0.30
     roadmap
    0.30
    ల
    0.30
     reconstitution
    0.30
     rebate
    0.30
     regeneration
    0.30
    Activations Density 0.181%

    No Known Activations