© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 2293
    Prev
    Next
    INDEX
    Explanations

    academic research papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    上涨
    0.55
     ถ้า
    0.54
    可以让
    0.54
     ব্যবসার
    0.51
     డబ్బు
    0.51
     аласыз
    0.51
    栤
    0.51
     మీరు
    0.50
     покупать
    0.50
    骂
    0.48
    POSITIVE LOGITS
     preclinical
    0.65
     ABSTRACT
    0.57
     clinical
    0.57
     immunohist
    0.57
     results
    0.56
     cytotoxic
    0.56
     research
    0.56
     PMID
    0.56
     PubMed
    0.56
     findings
    0.55
    Activations Density 0.172%

    No Known Activations