© 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. 63016
    Prev
    Next
    INDEX
    Explanations

    death of family members

    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
    loggedIn
    0.44
    nage
    0.43
     trabajan
    0.40
    newMark
    0.40
    微信
    0.40
    _{+}\
    0.40
     sienten
    0.40
     teman
    0.39
     उन्न
    0.39
     unve
    0.39
    POSITIVE LOGITS
     victim
    0.45
     prematurely
    0.44
     deleterious
    0.42
     erasing
    0.41
     disappears
    0.40
     destructive
    0.40
     zero
    0.39
     offensive
    0.39
    .`
    0.39
     नष्ट
    0.39
    Activations Density 0.003%

    No Known Activations