© 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. 151484
    Prev
    Next
    INDEX
    Explanations

    all

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

    emerges naturally, grip allows, but 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
    틋
    0.52
    คน
    0.49
    udni
    0.49
    ทย
    0.48
     שלה
    0.48
     приват
    0.48
    霟
    0.47
    קה
    0.47
    ປະກ
    0.47
    ላለ
    0.47
    POSITIVE LOGITS
     lubrication
    0.57
     veya
    0.54
     lubric
    0.52
     absorbs
    0.52
     hydraulics
    0.51
     produce
    0.49
     contains
    0.49
     produces
    0.49
     develops
    0.49
     water
    0.48
    Activations Density 0.001%

    No Known Activations