© 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. 157901
    Prev
    Next
    INDEX
    Explanations

    following prepositions or articles

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

    natural humility, wealth, clients

    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
    search
    0.58
    n
    0.55
    GN
    0.53
    v
    0.53
    at
    0.52
    en
    0.52
    smartphone
    0.51
    gn
    0.50
    encryption
    0.49
    Equations
    0.49
    POSITIVE LOGITS
    过度
    0.45
    ことに
    0.45
    ٥
    0.45
    лыми
    0.44
     gratuits
    0.44
    半分
    0.44
    试点
    0.43
     indiscrimin
    0.43
    慢性
    0.43
    
    0.43
    Activations Density 0.002%

    No Known Activations