© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 4362
    Prev
    Next
    INDEX
    Explanations

    `*(number)` citation pattern

    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
     عوامی
    0.26
    aneers
    0.25
     confuses
    0.24
     pubblici
    0.24
    ্যস্ত
    0.23
    কর্মী
    0.23
    孅
    0.23
    జాగా
    0.23
    尼亚克
    0.23
    哳
    0.23
    POSITIVE LOGITS
     supplement
    0.38
     suppl
    0.38
    Supplement
    0.36
    supplement
    0.36
     Suppl
    0.35
    Suppl
    0.35
     supl
    0.34
    issue
    0.33
     issue
    0.31
     Supplement
    0.31
    Activations Density 0.002%

    No Known Activations