© 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. 1587
    Prev
    Next
    INDEX
    Explanations

    depleted

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

    citations and references

    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
    ayutt
    0.31
    岖
    0.30
     navController
    0.30
    ్‌
    0.29
    ુલ
    0.29
    <unused50>
    0.29
     Шу
    0.29
    িবদ্ধ
    0.29
     Pogis
    0.29
    㬹
    0.29
    POSITIVE LOGITS
     Table
    0.35
    Table
    0.34
    SI
    0.33
     TABLE
    0.32
    <0xE2>
    0.31
    Abbreviations
    0.30
    TABLE
    0.30
    Figure
    0.29
    AR
    0.29
    −
    0.29
    Activations Density 0.173%

    No Known Activations