© 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. 53-GEMMASCOPE-2-RES-262K
    7. 40098
    Prev
    Next
    INDEX
    Explanations

    quantities involving "half"

    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_53_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
     Psychiatry
    0.36
     );
    0.35
     ហើយ
    0.35
    فيد
    0.35
    ចែកចាយ
    0.35
    了一個
    0.34
     নিজেই
    0.34
     дверей
    0.34
    েশ
    0.34
    ರಿದ
    0.34
    POSITIVE LOGITS
     ½
    0.59
     ¾
    0.59
     setengah
    0.57
     डेढ़
    0.57
    ½
    0.55
     ونص
    0.53
     demie
    0.53
     meia
    0.51
     half
    0.49
    半
    0.46
    Activations Density 0.004%

    No Known Activations