© 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. 60998
    Prev
    Next
    INDEX
    Explanations

    power dynamics and exploitation

    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
     catching
    0.46
    懲
    0.44
     तक
    0.42
     headway
    0.42
     ма
    0.42
     통
    0.42
     그러니까
    0.42
    ๖
    0.41
     пытается
    0.41
     overtaking
    0.41
    POSITIVE LOGITS
    JUNE
    0.45
    FUND
    0.43
     soov
    0.43
    UEN
    0.43
    ধানা
    0.42
    Producer
    0.41
    Recommend
    0.41
     offrire
    0.41
     concurso
    0.40
     சிகி
    0.40
    Activations Density 0.005%

    No Known Activations