© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2890
    Prev
    Next
    INDEX
    Explanations

    conjunctions and operators

    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_16_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
    0.64
     not
    0.57
    ol
    0.57
     NotFound
    0.57
    يام
    0.56
     is
    0.55
     _)
    0.55
    )
    0.55
    ോഷ്യ
    0.55
    </h3>
    0.54
    POSITIVE LOGITS
    и
    0.70
    jší
    0.61
     بودند
    0.61
    लाइन
    0.60
    ے
    0.60
    بی
    0.60
    ьте
    0.59
    "
    0.57
    اح
    0.56
    از
    0.55
    Activations Density 1.440%

    No Known Activations