© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15150
    Prev
    Next
    INDEX
    Explanations

    cheap or inexpensive

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

    simple, humble, inexpensive

    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_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
     peac
    0.43
     elegant
    0.39
     peacock
    0.39
     VIP
    0.39
     yachts
    0.39
    வனம்
    0.39
    高端
    0.38
    侖
    0.38
     consenting
    0.38
     vip
    0.37
    POSITIVE LOGITS
     lowly
    1.33
     humble
    1.17
     cheap
    1.16
    cheap
    1.07
     सस्ते
    1.06
    Cheap
    1.05
     inexpensive
    1.03
     low
    1.02
     деше
    1.02
     cheaply
    1.01
    Activations Density 0.952%

    No Known Activations