© 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. 31-GEMMASCOPE-2-RES-65K
    7. 8706
    Prev
    Next
    INDEX
    Explanations

    what we need

    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
    㠱
    0.45
    率
    0.44
     결과를
    0.43
    ूज
    0.43
    😠
    0.42
     அழ
    0.42
    కోవడం
    0.42
    聁
    0.42
     लेखन
    0.41
     দক্ষতা
    0.41
    POSITIVE LOGITS
     need
    0.42
     juggle
    0.42
     filed
    0.41
     chỉ
    0.41
     remaining
    0.40
     require
    0.40
     haem
    0.40
     will
    0.39
     filings
    0.39
    ('
    0.39
    Activations Density 0.003%

    No Known Activations