© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 16835
    Prev
    Next
    INDEX
    Explanations

    for missing and sexuality

    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
    CHAPTER
    0.42
     определяет
    0.32
     që
    0.31
     punishable
    0.31
     måtte
    0.30
     talisman
    0.30
    ɡ
    0.30
     stipulates
    0.30
    ‏:‏
    0.30
     shivering
    0.30
    POSITIVE LOGITS
     Sustainability
    0.41
     Economic
    0.40
     Outreach
    0.38
     Economics
    0.38
     Education
    0.37
     Humanities
    0.36
     Highlands
    0.36
     asuntos
    0.36
     Economy
    0.36
     assuntos
    0.35
    Activations Density 0.009%

    No Known Activations