© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5477
    Prev
    Next
    INDEX
    Explanations

    descriptive words followed by 'that'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
    做一个
    1.82
    一个人
    1.62
    𝗠
    1.59
     <$>
    1.57
    😅
    1.54
    🚩
    1.54
     =)
    1.52
     Choosing
    1.52
    𝗖
    1.51
     presenting
    1.51
    POSITIVE LOGITS
     heretofore
    1.89
     hitherto
    1.80
     sorely
    1.68
     variously
    1.60
     sempat
    1.50
     seldom
    1.49
     bitterly
    1.42
    頗
    1.39
     rarely
    1.39
     customarily
    1.39
    Activations Density 0.163%

    No Known Activations