© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44397
    Prev
    Next
    INDEX
    Explanations

    Indian Rupee and Indonesian Rupiah

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ጺ
    -2.50
    🫃
    -2.50
    u
    -2.48
    uttgart
    -2.45
    他
    -2.41
    i
    -2.34
    。
    -2.31
    y
    -2.31
    [
    -2.27
    ⟞
    -2.23
    POSITIVE LOGITS
     conjunction
    2.58
     letzte
    2.48
    蹕
    2.45
    荜
    2.41
    毳
    2.38
     frequentemente
    2.38
     offizielle
    2.31
     gesamte
    2.30
    ための
    2.30
     else
    2.30
    Activations Density 0.001%

    No Known Activations