© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5850
    Prev
    Next
    INDEX
    Explanations

    "you are" followed by a description

    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_31_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
    싫
    0.51
    וי
    0.50
     архіви
    0.48
    바일
    0.47
    環境
    0.47
    辦
    0.46
    我不
    0.45
    ปัจจุบัน
    0.44
    🫣
    0.44
    거든
    0.43
    POSITIVE LOGITS
     are
    0.53
     hereby
    0.52
     =
    0.52
     $=$
    0.51
     MUST
    0.50
     Tail
    0.49
     TWO
    0.49
     must
    0.48
     Liang
    0.47
     two
    0.46
    Activations Density 0.176%

    No Known Activations