© 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. 88124
    Prev
    Next
    INDEX
    Explanations

    still, continuing, or bump

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

    continue still

    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
     (
    0.40
     effectivement
    0.40
     restit
    0.38
     Nij
    0.37
     apari
    0.37
     [
    0.37
     Ley
    0.37
     Hugo
    0.37
     Thief
    0.37
    ამის
    0.36
    POSITIVE LOGITS
     nadal
    0.59
    仍
    0.54
     vẫn
    0.52
    依然
    0.52
     weiterhin
    0.51
     fortfarande
    0.51
    引き続き
    0.51
    仍然
    0.50
     stále
    0.48
     मिळत
    0.48
    Activations Density 0.043%

    No Known Activations