© 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. 208930
    Prev
    Next
    INDEX
    Explanations

    credit settlement

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

    why it

    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
     Tuj
    0.49
     አካ
    0.48
     má
    0.47
     pollutants
    0.46
     tuj
    0.45
     മി
    0.45
    5
    0.45
     ந
    0.45
     olursa
    0.44
     Schwarzen
    0.44
    POSITIVE LOGITS
    тельно
    0.46
    ジェ
    0.46
    接
    0.46
    不由
    0.44
    کی
    0.43
    井
    0.43
    "
    0.43
    นี้
    0.42
    ခင်
    0.42
    錯誤
    0.41
    Activations Density 0.001%

    No Known Activations