© 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. 155547
    Prev
    Next
    INDEX
    Explanations

    divorce or episode

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

    Self, Coin, Cover, They, Equally

    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
     inability
    0.49
     omission
    0.47
     crème
    0.47
     sauce
    0.47
     assassination
    0.47
     chance
    0.46
     deliverance
    0.46
    క
    0.46
     gonna
    0.46
     quill
    0.46
    POSITIVE LOGITS
     حص
    0.53
     لوی
    0.50
     لمع
    0.50
     مطرح
    0.50
     طور
    0.49
     ملك
    0.49
     পরিচালনা
    0.48
     மாசுபா
    0.47
     ملي
    0.46
    tcpHeader
    0.46
    Activations Density 0.000%

    No Known Activations