© 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. 43408
    Prev
    Next
    INDEX
    Explanations

    loss of or damage

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

    crafting, includes, realizing, saying, rapidly, May

    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
    י
    0.49
     sắt
    0.47
     设置
    0.45
    rove
    0.44
    硬件
    0.44
     veri
    0.43
     reag
    0.43
    ισμό
    0.42
    რ
    0.42
    стана
    0.42
    POSITIVE LOGITS
    ka
    0.49
     livre
    0.48
    ۰۰
    0.47
    갑
    0.47
     Cognitive
    0.46
    aller
    0.45
     cognitive
    0.44
    ミリ
    0.43
    ラベル
    0.43
     theor
    0.43
    Activations Density 0.001%

    No Known Activations