© 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. 175657
    Prev
    Next
    INDEX
    Explanations

    quantity and cost savings

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

    corrupt, diplomatic, wearable, bold, flower

    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
    ﻚ
    0.52
    Mahon
    0.52
    IVACON
    0.51
    тельской
    0.51
     Willoughby
    0.50
    моби
    0.49
    ಟ
    0.49
    Москва
    0.48
    макра
    0.48
    ﻥ
    0.48
    POSITIVE LOGITS
     overnight
    0.53
     बाब
    0.50
     verr
    0.50
     dan
    0.49
     /
    0.48
    /
    0.48
     erat
    0.48
     HAC
    0.46
     +
    0.46
     outfits
    0.46
    Activations Density 0.000%

    No Known Activations