© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 138916
    Prev
    Next
    INDEX
    Explanations

    obligations and regulations

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

    AntiGPT, modern, salt, google

    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
     formação
    0.60
     读取
    0.59
     formación
    0.56
     формирование
    0.54
    <unused20>
    0.53
     இரண்டு
    0.52
    AutoSize
    0.51
     调用
    0.50
     nossa
    0.50
    镞
    0.50
    POSITIVE LOGITS
    <start_of_image>
    0.48
    ↵↵
    0.46
     Scott
    0.43
    実は
    0.42
    <u>
    0.41
     hopelessly
    0.40
    curves
    0.39
    ↵↵↵
    0.38
    <strong>
    0.38
     curves
    0.38
    Activations Density 0.000%

    No Known Activations