© 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-65K
    7. 14660
    Prev
    Next
    INDEX
    Explanations

    planning and assuming

    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_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
     불안
    0.42
     ужа
    0.39
    ಾದ
    0.39
     บ่
    0.39
     системати
    0.39
    ङ
    0.38
    bigsqcup
    0.38
    땠
    0.38
    ያንዳ
    0.37
    考試
    0.37
    POSITIVE LOGITS
     thường
    0.46
    业务
    0.45
     you
    0.45
     go
    0.44
     già
    0.44
     usually
    0.44
     Final
    0.43
     обычно
    0.42
     already
    0.42
     goes
    0.42
    Activations Density 0.056%

    No Known Activations