© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54971
    Prev
    Next
    INDEX
    Explanations

    private, men, pure, sitting, isolated

    np_acts-logits-general · gemini-2.5-flash-lite

    wearables, Limit, ankle, Africa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    َنْ
    0.57
     effectuer
    0.46
    某种
    0.45
     producteurs
    0.45
    вла
    0.44
    愕
    0.44
    يمكن
    0.44
     аккумуля
    0.43
    燥
    0.43
    кому
    0.43
    POSITIVE LOGITS
     Jewish
    0.50
     Torah
    0.44
     where
    0.43
     Teacher
    0.43
    other
    0.42
     Fondation
    0.42
     teaching
    0.42
     L
    0.41
     theological
    0.41
     divine
    0.41
    Activations Density 0.000%

    No Known Activations