© 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. 40-GEMMASCOPE-2-RES-262K
    7. 10805
    Prev
    Next
    INDEX
    Explanations

    numbers and ordinals like ninth

    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_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
     hém
    0.45
    很重要
    0.45
     означа
    0.43
     molest
    0.43
    颞
    0.42
    的重要
    0.42
    тері
    0.42
    komst
    0.42
     मित्त
    0.42
     Includes
    0.42
    POSITIVE LOGITS
    9
    0.68
     ninth
    0.54
    lives
    0.53
    nine
    0.49
    veh
    0.49
     lives
    0.49
    me
    0.49
    ⁹
    0.48
    th
    0.48
    но
    0.48
    Activations Density 0.056%

    No Known Activations