© 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. 54663
    Prev
    Next
    INDEX
    Explanations

    Italian words starting with "sc"

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

    External Influences

    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
     Ос
    0.44
    ギリス
    0.39
    緒
    0.39
     예측
    0.38
    
    0.37
     пат
    0.37
    構
    0.36
             
    0.36
     భాష
    0.36
    seyside
    0.36
    POSITIVE LOGITS
     coordinated
    0.46
     Amended
    0.44
    empre
    0.42
    वा
    0.42
     मला
    0.41
    coordinated
    0.41
    parseInt
    0.41
    तियों
    0.41
     dici
    0.41
    瑪
    0.41
    Activations Density 0.000%

    No Known Activations