© 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. 24987
    Prev
    Next
    INDEX
    Explanations

    phrasal constructions

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

    AI Japan, charge, force

    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
     تساعد
    0.54
     يساعد
    0.48
     myös
    0.46
    ەکە
    0.43
    Explain
    0.42
    і
    0.42
     explain
    0.41
     reduces
    0.41
     explains
    0.41
     объяс
    0.40
    POSITIVE LOGITS
    olées
    0.47
    酝
    0.45
     unassuming
    0.43
     zewnętrzne
    0.43
    ısından
    0.41
     صہیونیت
    0.41
     havia
    0.41
     কঠিন
    0.40
     habíamos
    0.40
     haberse
    0.40
    Activations Density 0.000%

    No Known Activations