© 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. 172678
    Prev
    Next
    INDEX
    Explanations

    shopping cart

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

    European, following, topic, jealousy, stomach

    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
    萊
    0.53
    摑
    0.48
     বাড়তি
    0.47
     incentivize
    0.47
    促進
    0.46
    श्न
    0.46
     그러니까
    0.46
    ाइए
    0.46
    infodisc
    0.46
    駛
    0.46
    POSITIVE LOGITS
     wilderness
    0.51
    0.50
     many
    0.46
     I
    0.44
     con
    0.44
     ATV
    0.43
     realistic
    0.42
    ‬‬
    0.42
     Mooney
    0.42
    很难
    0.42
    Activations Density 0.001%

    No Known Activations