© 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-16K
    7. 11655
    Prev
    Next
    INDEX
    Explanations

    agricultural production and perjury

    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_16k_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
     ござい
    0.47
    遗传
    0.41
     ຈ
    0.41
     genetically
    0.41
    ACY
    0.41
     zmi
    0.41
    ړو
    0.40
     inherently
    0.40
     biologically
    0.38
    鶚
    0.38
    POSITIVE LOGITS
     oaths
    0.50
     sworn
    0.49
     swear
    0.46
     swearing
    0.46
     perjury
    0.45
     swears
    0.44
    Oath
    0.42
     oath
    0.41
     शपथ
    0.41
    눕
    0.40
    Activations Density 0.017%

    No Known Activations