© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 44864
    Prev
    Next
    INDEX
    Explanations

    application logic and experience

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     역할을
    0.42
    getStatus
    0.42
     сведения
    0.42
     ねえ
    0.40
    Status
    0.40
     essentiellement
    0.39
     funzioni
    0.39
    StarGo
    0.39
    頸
    0.38
     welche
    0.38
    POSITIVE LOGITS
    ﻛ
    0.50
    Mega
    0.46
    čili
    0.46
     Mega
    0.45
    kook
    0.45
    kii
    0.44
     उम्मीदवार
    0.43
     criminals
    0.43
     ফারুক
    0.43
     dece
    0.43
    Activations Density 0.012%

    No Known Activations