© 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. 163488
    Prev
    Next
    INDEX
    Explanations

    settle down

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

    settle, settling, settled; calm, resolve, decide

    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
     was
    0.72
    я
    0.68
     “
    0.66
    ı
    0.63
    ся
    0.62
     can
    0.59
     has
    0.59
    ne
    0.57
    ä
    0.57
    نا
    0.56
    POSITIVE LOGITS
     settle
    1.19
     settling
    1.16
     settles
    1.14
    Sett
    1.05
    sett
    0.98
     Settlement
    0.97
     settled
    0.94
     Sett
    0.93
     settlement
    0.91
    Settl
    0.86
    Activations Density 0.037%

    No Known Activations