© 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. 116922
    Prev
    Next
    INDEX
    Explanations

    foreign words and suffixes

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

    state = initialization

    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
    ル
    0.53
     operações
    0.51
    斯坦
    0.46
    創造
    0.46
    얄
    0.46
     ventas
    0.46
     operaciones
    0.46
    ミ
    0.46
    シャル
    0.46
    それぞれの
    0.46
    POSITIVE LOGITS
     其实
    0.46
     হওয়া
    0.44
     Redis
    0.41
    的时
    0.41
    ables
    0.40
     été
    0.40
    ometer
    0.40
    ibe
    0.40
    abe
    0.39
    ically
    0.39
    Activations Density 0.000%

    No Known Activations