© 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. 248051
    Prev
    Next
    INDEX
    Explanations

    emerging market economics

    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
    ósfera
    0.58
     aparat
    0.56
     영
    0.55
     או
    0.53
     querer
    0.52
     ឬ
    0.49
    AMA
    0.48
     estar
    0.47
     или
    0.46
     módulo
    0.46
    POSITIVE LOGITS
    同学
    0.49
    亮度
    0.47
     dynamite
    0.44
    erville
    0.43
    校
    0.43
    能量
    0.42
    اولة
    0.42
     fireworks
    0.42
     خارجية
    0.41
    υγ
    0.41
    Activations Density 0.001%

    No Known Activations