© 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. 115481
    Prev
    Next
    INDEX
    Explanations

    web site visitors

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

    asset separation and tax optimization

    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
    盡
    0.46
     প্রমুখ
    0.43
     Brook
    0.40
    继续
    0.39
    同樣
    0.39
    擔任
    0.39
     LOTRAchievement
    0.39
    滥
    0.39
    繼續
    0.38
     Roz
    0.38
    POSITIVE LOGITS
    jats
    0.48
     chén
    0.44
     đòi
    0.44
     вами
    0.42
    ampaikan
    0.42
    ი
    0.41
     domanda
    0.41
    ばん
    0.41
     PERSON
    0.40
    ্সর
    0.40
    Activations Density 0.003%

    No Known Activations