© 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. 1310
    Prev
    Next
    INDEX
    Explanations

    research and study

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

    research contexts

    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
    elum
    0.39
     समाय
    0.39
     সমাবে
    0.36
     സമ്പ
    0.36
    Ყ
    0.36
    ையா
    0.35
    typicode
    0.35
    เวอร์
    0.35
     enemigos
    0.34
    鬧
    0.34
    POSITIVE LOGITS
     research
    4.94
    research
    4.59
     Research
    4.19
    研究
    4.19
    Research
    4.19
     연구
    4.16
     RESEARCH
    4.16
    RESEARCH
    4.06
     penelitian
    3.83
     researches
    3.77
    Activations Density 0.606%

    No Known Activations