© 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. 190003
    Prev
    Next
    INDEX
    Explanations

    international scripts and phrases

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

    bullet points

    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
    erald
    0.50
    σης
    0.49
     健康
    0.49
     건강
    0.48
     ব্যাকটেরিয়া
    0.47
    블릿
    0.47
    insertCell
    0.45
    룡
    0.45
    ላል
    0.45
    꼽
    0.45
    POSITIVE LOGITS
     ier
    0.51
    }
    0.49
     scherm
    0.44
     do
    0.44
     sul
    0.42
     urna
    0.42
     ui
    0.42
     kr
    0.41
    در
    0.41
    的意思
    0.41
    Activations Density 0.001%

    No Known Activations