© 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. 33075
    Prev
    Next
    INDEX
    Explanations

    perfect following nouns

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

    perfect plus descriptive noun

    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
     as
    0.89
    ;
    0.84
     hurried
    0.74
     impressive
    0.70
    ‌ای
    0.68
     up
    0.68
     guarded
    0.68
     very
    0.66
     \
    0.65
     improved
    0.65
    POSITIVE LOGITS
     perfeito
    1.15
     perfecto
    1.11
    完美的
    1.06
     PERFECT
    1.05
     perfekte
    1.04
     Perfecto
    1.03
    Perfect
    1.02
     perfekt
    1.02
     parfaite
    1.02
     perfetto
    1.00
    Activations Density 0.059%

    No Known Activations