© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 3230
    Prev
    Next
    INDEX
    Explanations

    data privacy concerns

    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_40_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
    检验
    0.47
     Vật
    0.42
     接
    0.41
    拄
    0.41
     geology
    0.40
    接
    0.40
     chromatic
    0.39
    蕈
    0.39
     decad
    0.39
     fungus
    0.39
    POSITIVE LOGITS
     privacy
    2.63
     Privacy
    2.53
    Privacy
    2.45
    privacy
    2.38
    隐私
    2.25
     privacidade
    2.05
     privacidad
    1.94
     Datenschutz
    1.91
     गोपनीयता
    1.91
     Privacidade
    1.63
    Activations Density 0.422%

    No Known Activations