© 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. 15666
    Prev
    Next
    INDEX
    Explanations

    again

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

    day and continuation markers

    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
     lorsqu
    0.52
     ஆதார
    0.50
    बल
    0.48
     जना
    0.47
     jamás
    0.43
     limiti
    0.42
     źród
    0.42
    𠃌
    0.42
     efic
    0.41
    एपी
    0.41
    POSITIVE LOGITS
     আবারও
    0.85
    再び
    0.82
     again
    0.75
     novamente
    0.74
     erneut
    0.71
    引き続き
    0.68
     Again
    0.68
    继续
    0.68
    再度
    0.68
     συνέχ
    0.68
    Activations Density 0.102%

    No Known Activations