© 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. 135176
    Prev
    Next
    INDEX
    Explanations

    listing contents or topics

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

    "resonate with" and "include"

    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
    лева
    0.61
    리면
    0.51
     ordine
    0.50
    
    0.50
     ٣
    0.50
     وفي
    0.49
     efectivamente
    0.48
    ᱙
    0.47
     Ünivers
    0.46
     ecuaciones
    0.46
    POSITIVE LOGITS
     moniker
    0.53
     name
    0.45
     financing
    0.44
     bel
    0.43
     deform
    0.43
    ById
    0.42
     plumbing
    0.42
     complex
    0.41
     helix
    0.41
     integral
    0.41
    Activations Density 0.000%

    No Known Activations