© 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. 40-GEMMASCOPE-2-RES-65K
    7. 2586
    Prev
    Next
    INDEX
    Explanations

    half the, half of, half a

    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_40_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
    อุ
    0.41
    Authentication
    0.40
    ９
    0.39
    ų
    0.39
    every
    0.38
    anyone
    0.38
    ทุก
    0.38
    ulis
    0.37
    CATEGORY
    0.37
    Carlos
    0.37
    POSITIVE LOGITS
     half
    0.98
     Half
    0.94
     نصف
    0.87
    half
    0.85
    Half
    0.84
     HALF
    0.80
    半
    0.77
     आधा
    0.74
     दर्जन
    0.74
     dozen
    0.74
    Activations Density 0.089%

    No Known Activations