© 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. 60510
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    planetary defense programs

    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
     equalization
    0.46
    可能
    0.45
    可能です
    0.44
     possibly
    0.44
     πι
    0.43
    다른
    0.41
     可能
    0.41
     제
    0.40
     FL
    0.40
     가능
    0.39
    POSITIVE LOGITS
     była
    0.47
     পরাজিত
    0.47
     afgelopen
    0.47
     asal
    0.47
     során
    0.46
     atacar
    0.45
     જીવન
    0.45
    षित
    0.45
     após
    0.45
     reje
    0.45
    Activations Density 0.000%

    No Known Activations