© 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. 51176
    Prev
    Next
    INDEX
    Explanations

    before or after

    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
     assigns
    0.41
     ಅವರಿಗೆ
    0.41
    +|\
    0.40
     getName
    0.39
     affirms
    0.39
    変化
    0.39
     মাসুদ
    0.39
     obtains
    0.39
     computes
    0.39
    ಿದ್ದಾನೆ
    0.38
    POSITIVE LOGITS
     หลังจาก
    0.45
    odendron
    0.44
     προς
    0.44
     pode
    0.43
     graças
    0.42
     кілька
    0.42
     teilweise
    0.42
    噹
    0.42
     algumas
    0.42
    öl
    0.41
    Activations Density 0.016%

    No Known Activations