© 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. 1987
    Prev
    Next
    INDEX
    Explanations

    qualitative descriptors

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

    multiple ways

    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
     ☑
    0.22
     यदि
    0.21
    🎅
    0.19
     USING
    0.19
     에서
    0.19
     Recomend
    0.19
    제의
    0.19
     如果
    0.19
    💥
    0.19
     中的
    0.19
    POSITIVE LOGITS
     unrelenting
    0.18
     cherished
    0.18
     meagre
    0.17
     nuanced
    0.17
     proverbial
    0.17
     reimag
    0.17
     palpable
    0.17
     swiftly
    0.16
     multimillion
    0.16
     richly
    0.16
    Activations Density 0.363%

    No Known Activations