© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 10196
    Prev
    Next
    INDEX
    Explanations

    fresh desk graduate sales

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ệ
    0.44
     vosotros
    0.43
     upbringing
    0.43
     좋아하는
    0.41
    ထဲ
    0.40
    უს
    0.39
     הו
    0.39
    ्ये
    0.38
    $}
    0.38
     métier
    0.38
    POSITIVE LOGITS
     fresh
    1.15
     Fresh
    1.13
    Fresh
    1.09
    fresh
    1.05
     FRESH
    1.02
     freshness
    1.01
    refresh
    0.99
     fresca
    0.97
     fres
    0.96
     Fres
    0.94
    Activations Density 0.006%

    No Known Activations