© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1150
    Prev
    Next
    INDEX
    Explanations

    S, A pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    🔛
    1.01
    bm
    1.00
    🔉
    0.94
     rmse
    0.93
    🔃
    0.93
    pca
    0.93
     edt
    0.92
    bw
    0.91
    rw
    0.91
    otf
    0.91
    POSITIVE LOGITS
     B
    2.70
     C
    2.56
     E
    2.54
     D
    2.50
     F
    2.34
     M
    2.24
     S
    2.23
     L
    2.21
     G
    2.20
     T
    2.20
    Activations Density 1.955%

    No Known Activations