© 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. 44630
    Prev
    Next
    INDEX
    Explanations

    more

    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
     moindre
    0.45
    Retour
    0.43
     যাবতীয়
    0.42
    niejszych
    0.42
     autres
    0.41
     nærm
    0.40
    othyroidism
    0.40
    이가
    0.39
    ފ
    0.39
     termed
    0.39
    POSITIVE LOGITS
     lisää
    0.63
     увеличения
    0.56
     збіль
    0.52
     বাড়ানোর
    0.51
     увеличить
    0.51
     เพิ่ม
    0.49
     zwięks
    0.49
     늘
    0.46
     বাড়ানো
    0.46
     menambah
    0.46
    Activations Density 0.059%

    No Known Activations