© 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. 16678
    Prev
    Next
    INDEX
    Explanations

    I thought or I am

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

    I express opinion/sentiment

    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
    ですが
    0.57
    のですが
    0.52
    であれば
    0.49
    でしたが
    0.48
    Remark
    0.47
    மாகவும்
    0.46
    ✍
    0.46
    또한
    0.46
    持續
    0.45
    然而
    0.44
    POSITIVE LOGITS
     exclaimed
    0.62
     nowe
    0.54
    这不是
    0.51
     nació
    0.49
     these
    0.48
     nowy
    0.46
     gotta
    0.46
     forgot
    0.46
     cried
    0.46
     didn
    0.45
    Activations Density 0.133%

    No Known Activations