© 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. 90176
    Prev
    Next
    INDEX
    Explanations

    words before phrases

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

    witnessed their

    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
    ếu
    0.58
    썩
    0.52
    香港
    0.49
    严重
    0.46
     吴
    0.45
    零
    0.44
    嚴重
    0.44
     deplete
    0.44
    这么
    0.44
    这里的
    0.44
    POSITIVE LOGITS
    ذیر
    0.54
    ک
    0.50
     Ett
    0.47
    bh
    0.46
    dal
    0.46
     ویک
    0.46
    ohl
    0.45
     yönt
    0.45
    fw
    0.45
    fecture
    0.45
    Activations Density 0.001%

    No Known Activations