© 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. 5032
    Prev
    Next
    INDEX
    Explanations

    using variables

    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
     cornea
    0.43
     carvings
    0.43
     spores
    0.42
     carving
    0.42
    豪華
    0.42
    dogs
    0.41
     layers
    0.41
    糰
    0.41
     carved
    0.40
    hampton
    0.40
    POSITIVE LOGITS
    Variables
    0.80
    变量
    0.79
     Variables
    0.77
     Variablen
    0.75
     VARIABLE
    0.75
     переменных
    0.73
     variables
    0.72
     variable
    0.70
    Variable
    0.67
    VARIABLES
    0.67
    Activations Density 0.401%

    No Known Activations