© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12273
    Prev
    Next
    INDEX
    Explanations

    java, scala, resources

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

    file paths in source code, particularly the "main" directory or component in a path structure.

    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
    ския
    -2.09
    ,"
    -1.67
    }$
    -1.60
    шивания
    -1.53
     腿
    -1.53
     oktober
    -1.49
    piration
    -1.48
     listopada
    -1.48
    ($__
    -1.47
    ":
    -1.46
    POSITIVE LOGITS
     этих
    1.63
    無論
    1.51
     that
    1.38
     těchto
    1.38
     either
    1.34
     kook
    1.33
     dauern
    1.30
     比較
    1.29
     inol
    1.29
    所謂
    1.25
    Activations Density 0.002%

    No Known Activations