© 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. 3537
    Prev
    Next
    INDEX
    Explanations

    "That", "It", "Of", "So"

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

    end of sentence or list item

    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
     arti
    0.56
     inti
    0.55
    RAC
    0.50
     dic
    0.49
    ري
    0.49
    лізу
    0.49
     فِي
    0.48
    Ῥ
    0.48
    روت
    0.48
     countries
    0.47
    POSITIVE LOGITS
     That
    0.75
     Therefore
    0.69
     However
    0.68
     But
    0.63
     It
    0.60
     Of
    0.59
     Adding
    0.59
     Conversely
    0.59
     So
    0.58
     Chances
    0.58
    Activations Density 0.001%

    No Known Activations