© 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. 143502
    Prev
    Next
    INDEX
    Explanations

    types of custom limits

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

    specific phrases or terms

    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
     allerdings
    0.47
    మే
    0.46
    Ꮞ
    0.40
    рас
    0.40
     Acest
    0.39
     எனவே
    0.38
     this
    0.38
     Brie
    0.38
     زد
    0.38
     Elim
    0.38
    POSITIVE LOGITS
     mỹ
    0.51
     mathvariant
    0.47
    nH
    0.47
    の種類
    0.47
     कस्टम
    0.46
    💄
    0.45
     gốc
    0.45
     inoxyd
    0.44
     cả
    0.43
     giấy
    0.42
    Activations Density 0.001%

    No Known Activations