© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 54202
    Prev
    Next
    INDEX
    Explanations

    scandalous affairs and conflicts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     mandible
    0.49
     Preschool
    0.48
     propane
    0.47
     campione
    0.46
     посмотреть
    0.46
    括号
    0.46
    牦
    0.46
     बढ़ोतरी
    0.45
     preschoolers
    0.45
     verduras
    0.44
    POSITIVE LOGITS
     blackmail
    0.45
     उसने
    0.43
     estranged
    0.42
    Zh
    0.40
     vamp
    0.40
    Ժ
    0.40
     guilty
    0.39
     secretly
    0.38
     accusation
    0.38
     драма
    0.37
    Activations Density 0.050%

    No Known Activations