© 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-16K
    7. 12830
    Prev
    Next
    INDEX
    Explanations

    "in the"

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

    in context

    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_16k_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
    ®.
    0.48
    ™.
    0.47
     उनका
    0.45
    mane
    0.43
     essi
    0.43
    %.
    0.40
    €.
    0.40
    МО
    0.40
     그래서
    0.39
    அத
    0.38
    POSITIVE LOGITS
    出现在
    0.80
    在新
    0.78
    នៅក្នុង
    0.77
     ở
    0.77
     във
    0.75
     στην
    0.75
     لدى
    0.75
     فى
    0.74
    在中
    0.73
     katika
    0.73
    Activations Density 1.250%

    No Known Activations