© 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. 2221
    Prev
    Next
    INDEX
    Explanations

    can lead to

    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
     in
    0.75
    在
    0.56
     в
    0.46
    iki
    0.45
    ék
    0.45
    se
    0.42
    ,
    0.42
    ography
    0.41
     on
    0.41
     desea
    0.41
    POSITIVE LOGITS
    N
    0.42
    T
    0.37
    doesn
    0.37
    ת
    0.35
    D
    0.34
    。
    0.34
    R
    0.33
    డియో
    0.33
    तमंद
    0.33
    this
    0.33
    Activations Density 0.241%

    No Known Activations