© 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. 16355
    Prev
    Next
    INDEX
    Explanations

    Westside, missing word

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

    contracted forms like "let's"

    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
              
    0.45
    <h2>
    0.45
    ↵↵↵↵↵
    0.44
       
    0.43
    <h3>
    0.42
        
    0.39
    ⇒
    0.39
    <blockquote>
    0.38
    ariamente
    0.38
    ↵↵↵↵
    0.38
    POSITIVE LOGITS
     cuffs
    0.46
     jeux
    0.44
     grooves
    0.44
     vassals
    0.44
     lézards
    0.44
     functionals
    0.43
     mêmes
    0.42
     annuities
    0.42
     fluids
    0.42
     prairies
    0.42
    Activations Density 0.000%

    No Known Activations