© 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. 164413
    Prev
    Next
    INDEX
    Explanations

    award happy safety

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

    focus on task 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
     美国
    0.52
     dh
    0.51
    μπ
    0.50
     Colonies
    0.50
     ativos
    0.49
     Dhoni
    0.49
    婭
    0.49
     Dh
    0.49
    ણી
    0.49
    ဓာ
    0.49
    POSITIVE LOGITS
    gs
    0.54
    ancourt
    0.53
    fue
    0.49
    zewski
    0.49
    enqueue
    0.48
    adding
    0.48
    remove
    0.47
    disk
    0.46
    fetching
    0.46
    setup
    0.46
    Activations Density 0.000%

    No Known Activations