© 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. 17362
    Prev
    Next
    INDEX
    Explanations

    postal codes, lithium, exhibition stands

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

    code or mathematical symbols

    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
     গর
    0.45
    മ്ബ
    0.38
    کش
    0.37
    𝐸
    0.37
    𝐵
    0.35
    វេល
    0.35
    krom
    0.35
    𝑅
    0.35
    ⽅
    0.35
    😬
    0.34
    POSITIVE LOGITS
    ทั้ง
    0.43
    そもそも
    0.40
     neither
    0.38
    <start_of_image>
    0.38
    ꗟ
    0.38
    neither
    0.37
             
    0.37
    MenuActive
    0.36
    ;;)
    0.36
    തിനാ
    0.36
    Activations Density 0.148%

    No Known Activations