© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 63509
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
    า
    0.40
    est
    0.38
    BagConstraints
    0.37
    latan
    0.36
    otan
    0.36
     Ba
    0.35
    買取
    0.35
     Black
    0.35
    uş
    0.35
     HC
    0.35
    POSITIVE LOGITS
    \%).
    0.42
     keing
    0.40
    冢
    0.40
    \%)
    0.40
     eventos
    0.39
    شاركة
    0.38
     بالج
    0.38
     событий
    0.38
     segni
    0.37
     eventi
    0.37
    Activations Density 0.014%

    No Known Activations