© 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. 41-GEMMASCOPE-2-RES-262K
    7. 25008
    Prev
    Next
    INDEX
    Explanations

    half and halves

    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_all/layer_41_width_262k_l0_big
    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
     ट्रिपल
    0.47
    三重
    0.45
    triple
    0.44
    魉
    0.41
    ƙ
    0.39
    ลาคม
    0.38
     triple
    0.38
     ভুট্ট
    0.37
     tiga
    0.37
    Triple
    0.37
    POSITIVE LOGITS
     half
    2.45
    Half
    2.31
     Half
    2.25
    half
    2.20
     halves
    2.05
    半
    2.03
     HALF
    1.91
    HALF
    1.88
     полови
    1.80
     halve
    1.79
    Activations Density 0.012%

    No Known Activations