© 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. 130988
    Prev
    Next
    INDEX
    Explanations

    Belt and Road Initiative

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

    religious cults, historical context

    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
     صالح
    0.50
     wire
    0.47
    usable
    0.44
    heus
    0.44
    وات
    0.43
    ip
    0.43
    &$
    0.41
    iesen
    0.41
    確
    0.41
     clustered
    0.40
    POSITIVE LOGITS
     Regulations
    0.53
     Capítulo
    0.52
     Kapitel
    0.50
     Chapter
    0.48
     Muhammadu
    0.47
    龅
    0.47
     Valuation
    0.47
     Fungsi
    0.47
     grundsätzlich
    0.46
    Protein
    0.46
    Activations Density 0.000%

    No Known Activations