© 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. 155232
    Prev
    Next
    INDEX
    Explanations

    identified in

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

    EU, power, cancellation, archive

    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
     tỏa
    0.55
     由于
    0.54
     yǔ
    0.53
    谥
    0.52
     phù
    0.51
     VEGF
    0.51
     tú
    0.50
     夜
    0.50
     mesenchymal
    0.49
     ✨
    0.48
    POSITIVE LOGITS
    growing
    0.49
    า
    0.47
    ea
    0.46
    riving
    0.46
    meas
    0.46
    entre
    0.46
    serious
    0.46
    reci
    0.45
    earnings
    0.45
    rap
    0.45
    Activations Density 0.001%

    No Known Activations