© 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. 89799
    Prev
    Next
    INDEX
    Explanations

    agreement, jurisdiction, safely, button

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

    product category

    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
    csak
    0.56
     Μα
    0.50
     Май
    0.50
    殃
    0.50
     حا
    0.49
    ൂടെ
    0.49
     élo
    0.49
    邈
    0.49
    ⵅ
    0.49
     Agust
    0.48
    POSITIVE LOGITS
    \
    0.49
     trajectories
    0.44
     oversized
    0.44
    י
    0.43
    ωση
    0.43
    i
    0.43
    READY
    0.42
     trajectory
    0.41
    গম
    0.41
    内容
    0.41
    Activations Density 0.000%

    No Known Activations