© 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. 2898
    Prev
    Next
    INDEX
    Explanations

    prohibition and limitations

    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
    ana
    0.80
    ر
    0.66
    re
    0.64
    ina
    0.63
    ik
    0.59
    ears
    0.59
    r
    0.57
     Abia
    0.57
    ari
    0.57
    ü
    0.56
    POSITIVE LOGITS
     desarroll
    0.64
    ј
    0.52
    雖然
    0.50
    <0xA8>
    0.48
    闿
    0.48
     ,
    0.48
    цы
    0.48
    ,*
    0.48
     proporcionan
    0.47
    จะ
    0.47
    Activations Density 0.167%

    No Known Activations