© 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. 89899
    Prev
    Next
    INDEX
    Explanations

    words related to Milan

    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
    アレ
    0.44
     naman
    0.44
     насеље
    0.43
    Included
    0.42
    AppState
    0.41
    FLP
    0.40
     tillegg
    0.40
    읊
    0.40
    pValue
    0.40
     namn
    0.40
    POSITIVE LOGITS
     чтобы
    0.53
    🥫
    0.53
    )^
    0.50
    ίζουν
    0.48
     सहकारी
    0.47
     ресторан
    0.46
    विण्यासाठी
    0.46
    াহীন
    0.45
     vários
    0.45
    ίζει
    0.45
    Activations Density 0.001%

    No Known Activations