© 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. 132024
    Prev
    Next
    INDEX
    Explanations

    foreign words

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

    functional words and relationships

    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
     u
    0.52
     примене
    0.47
     uitge
    0.47
    窅
    0.46
     уч
    0.44
     반영
    0.43
     <
    0.43
     diterapkan
    0.43
     drawRight
    0.43
     альбом
    0.43
    POSITIVE LOGITS
    一
    0.51
    до
    0.47
     Boga
    0.47
    ה
    0.47
    packageName
    0.45
    ামি
    0.45
    डाउन
    0.45
    C
    0.45
    сла
    0.44
    Бо
    0.44
    Activations Density 0.000%

    No Known Activations