© 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. 52761
    Prev
    Next
    INDEX
    Explanations

    parental leave, expulsion, weight management

    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
     fluores
    0.54
    :</
    0.53
     chit
    0.51
     aseptic
    0.50
     firmware
    0.50
     fluorescent
    0.48
     rech
    0.48
     purpose
    0.47
     offici
    0.47
     offerings
    0.46
    POSITIVE LOGITS
    ст
    0.51
    рт
    0.49
    ikker
    0.49
    lastName
    0.48
    ými
    0.47
    пол
    0.46
    ố
    0.44
    ndrome
    0.44
    िय
    0.43
    adamente
    0.43
    Activations Density 0.003%

    No Known Activations