© 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. 40-GEMMASCOPE-2-RES-65K
    7. 56140
    Prev
    Next
    INDEX
    Explanations

    Hindi and English bilingual text

    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_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ತುಂಬಾ
    0.53
    arsis
    0.48
    ἆ
    0.45
     Moral
    0.44
    গিরই
    0.44
     Луч
    0.43
     मीनिंग
    0.43
     Mud
    0.43
     murió
    0.42
     Tijdens
    0.41
    POSITIVE LOGITS
    저
    0.39
     ||
    0.37
     વડે
    0.35
    ")]
    0.35
    abilities
    0.34
     programmed
    0.34
     thang
    0.34
    }^{
    0.33
     scenarios
    0.33
     dioxane
    0.33
    Activations Density 0.002%

    No Known Activations