© 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. 63973
    Prev
    Next
    INDEX
    Explanations

    introverted or extroverted

    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
    тей
    0.48
    чеб
    0.45
    хар
    0.43
    зу
    0.43
     биологи
    0.43
    氅
    0.43
    ла
    0.42
    两年
    0.42
    ние
    0.42
    че
    0.42
    POSITIVE LOGITS
     atrocities
    0.49
     genocide
    0.48
     Youtube
    0.47
    Youtube
    0.45
     YouTube
    0.45
     horrific
    0.44
     impromptu
    0.44
     instantly
    0.44
     like
    0.43
    iflix
    0.43
    Activations Density 0.007%

    No Known Activations