© 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-262K
    7. 11549
    Prev
    Next
    INDEX
    Explanations

    conditional statements like if/else

    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_262k_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
    あります
    0.54
     utilisez
    0.51
     utilisent
    0.46
    ע
    0.46
    פ
    0.46
    مپ
    0.45
    你看
    0.45
    કો
    0.45
    מד
    0.45
    من
    0.44
    POSITIVE LOGITS
    0.53
     "")
    0.52
     )
    0.46
     ==
    0.44
     is
    0.43
     zero
    0.43
     !=
    0.42
     که
    0.42
     que
    0.42
     k
    0.41
    Activations Density 0.026%

    No Known Activations