© 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-262K
    7. 27828
    Prev
    Next
    INDEX
    Explanations

    treating people as property

    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_262k_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
    ნიშვნ
    0.45
    VerFile
    0.44
    ্ের
    0.43
    تھی
    0.42
     umpire
    0.41
     rebounding
    0.41
     ధ
    0.40
     المسافه
    0.40
    绁
    0.40
    ゾート
    0.39
    POSITIVE LOGITS
     as
    0.42
    atek
    0.38
     Growers
    0.38
    tek
    0.37
     §
    0.37
    hors
    0.36
     ain
    0.36
    ╲
    0.36
    felt
    0.36
    }\,
    0.35
    Activations Density 0.000%

    No Known Activations