© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185064
    Prev
    Next
    INDEX
    Explanations

    money, status, and events

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

    realistic expectations

    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
    Negative Logits
    å
    0.53
    čí
    0.51
    я
    0.51
    humidité
    0.50
    锌
    0.50
     жидко
    0.49
    nál
    0.49
    가
    0.49
    adece
    0.48
     परीक्षण
    0.48
    POSITIVE LOGITS
     month
    0.47
     money
    0.46
     demand
    0.44
     coast
    0.43
     evolution
    0.43
     reconsider
    0.43
     obscene
    0.43
     disillusioned
    0.43
     frustrated
    0.42
     astonished
    0.42
    Activations Density 0.002%

    No Known Activations