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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 53736
    Prev
    Next
    INDEX
    Explanations

    friend, friendship

    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_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
    朋友
    0.52
    on
    0.47
     friends
    0.45
    ။
    0.42
     दोस्तों
    0.41
    Nic
    0.41
    Graz
    0.41
     ఉద్య
    0.41
    arab
    0.40
    ᅨ
    0.39
    POSITIVE LOGITS
    谊
    0.63
    ships
    0.57
     детства
    0.55
    誼
    0.52
    ship
    0.50
    lier
    0.50
     zone
    0.46
     zones
    0.45
     মিলে
    0.45
     ínt
    0.44
    Activations Density 0.023%

    No Known Activations