© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9958
    Prev
    Next
    INDEX
    Explanations

    words ending in -er

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

    words ending in -er or -or

    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_40_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
        
    0.50
    ब
    0.47
    이
    0.46
    ت
    0.46
    한
    0.46
    Dat
    0.45
    ദേശം
    0.45
    مان
    0.45
    場
    0.45
    تس
    0.44
    POSITIVE LOGITS
     extraordinaire
    0.88
    锏
    0.50
     extraordin
    0.48
    gebnis
    0.48
     setia
    0.46
     beware
    0.44
     მან
    0.44
     modelBuilder
    0.44
    gebnisse
    0.43
    outes
    0.43
    Activations Density 0.864%

    No Known Activations