© 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. 40-GEMMASCOPE-2-RES-262K
    7. 851
    Prev
    Next
    INDEX
    Explanations

    paper sizes

    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_40_width_262k_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
     নিদর্শন
    0.42
     intestinal
    0.40
     attractions
    0.40
     bowel
    0.39
    澗
    0.36
     chewing
    0.35
     malls
    0.35
    कोष्ठ
    0.35
    itih
    0.35
     Attractions
    0.34
    POSITIVE LOGITS
    纸
    0.55
    paper
    0.54
     paper
    0.53
     Paper
    0.50
    Paper
    0.48
    ]{
    0.46
    紙
    0.42
     पेपर
    0.41
     fontsize
    0.40
     бумаги
    0.40
    Activations Density 0.001%

    No Known Activations