© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101503
    Prev
    Next
    INDEX
    Explanations

    ko followed by domain names, code, or place names

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

    the substring "ko" in code and text, particularly in variable names, library names, and URLs.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    ဴ
    -3.22
    ścioła
    -2.69
    lossians
    -2.63
    m
    -2.63
    rentiel
    -2.50
    a
    -2.39
    इटम
    -2.34
    of
    -2.33
    inigung
    -2.22
    垸
    -2.22
    POSITIVE LOGITS
    0
    2.97
     Meilleures
    2.52
     Meksika
    2.48
    ко
    2.45
    ⟣
    2.42
     médaille
    2.42
    𖣘
    2.36
    ኧ
    2.33
     chaqueta
    2.33
    状況
    2.30
    Activations Density 0.012%

    No Known Activations