© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8520
    Prev
    Next
    INDEX
    Explanations

    acknowledgments and funding

    np_acts-logits-general · gemini-2.5-flash-lite

    acknowledgments and funding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     шар
    0.49
    ழுக
    0.47
    摭
    0.47
    গন্ধ
    0.46
    视图
    0.46
    険
    0.46
    వ్వు
    0.45
    あなたの
    0.45
    এবার
    0.44
    边缘
    0.44
    POSITIVE LOGITS
     contributed
    0.74
     \
    0.59
     †
    0.59
     presented
    0.58
     received
    0.57
     funded
    0.56
    *
    0.54
     This
    0.54
     acknowledges
    0.54
     participated
    0.53
    Activations Density 0.026%

    No Known Activations