© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7811
    Prev
    Next
    INDEX
    Explanations

    vintage and classic items

    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_31_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
    例文
    0.46
     censoring
    0.43
    溶液
    0.40
     phosphorylated
    0.40
     comunicazione
    0.38
    📵
    0.38
    তাহাকে
    0.38
     judíos
    0.38
     eukaryotic
    0.38
    }}:=\
    0.37
    POSITIVE LOGITS
     affordability
    0.55
     upgrades
    0.51
     Vintage
    0.50
    価格
    0.49
    vintage
    0.49
     ремон
    0.49
     upgrade
    0.48
    Vintage
    0.48
     resale
    0.48
     Classic
    0.47
    Activations Density 0.185%

    No Known Activations