© 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. 181782
    Prev
    Next
    INDEX
    Explanations

    financial terms and actions

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

    introduces or elaborates

    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
    df
    0.49
    t
    0.48
    中山
    0.46
    水素
    0.46
     потер
    0.46
    r
    0.46
    Δ
    0.46
    ϟ
    0.46
    
    0.46
    르
    0.46
    POSITIVE LOGITS
     snacks
    0.52
     snacking
    0.47
     diners
    0.46
     للغاية
    0.46
     kimchi
    0.46
     appetizers
    0.46
     discoveries
    0.46
     给
    0.46
     Cuenta
    0.45
    eliest
    0.45
    Activations Density 0.000%

    No Known Activations