© 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. 61255
    Prev
    Next
    INDEX
    Explanations

    impact, current, patient, manufacturer

    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
     laki
    0.47
    D
    0.47
    ')->
    0.46
     $)
    0.46
    有过
    0.46
     crescita
    0.46
     কর্তা
    0.43
     idols
    0.43
    ewhat
    0.42
     grat
    0.42
    POSITIVE LOGITS
     Being
    0.46
    ｃ
    0.44
     Parade
    0.40
     दुनिया
    0.39
     ظِلِّ
    0.39
    rotechn
    0.39
     ہیں۔
    0.39
     Bonnie
    0.39
    အချိန်
    0.39
     چلا
    0.39
    Activations Density 0.009%

    No Known Activations