© 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. 2287
    Prev
    Next
    INDEX
    Explanations

    units of data or structure

    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
    ;
    0.75
     t
    0.61
    ক
    0.55
    ید
    0.55
    ERS
    0.55
    <strong>
    0.50
    ک
    0.50
    2
    0.50
    し
    0.49
    ه‌
    0.49
    POSITIVE LOGITS
     dezelfde
    0.59
     její
    0.57
     svého
    0.57
     privadas
    0.57
     básicas
    0.55
     próprias
    0.55
     enviado
    0.55
     distinta
    0.55
     vendedor
    0.54
     возмо
    0.53
    Activations Density 0.515%

    No Known Activations