© 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. 102758
    Prev
    Next
    INDEX
    Explanations

    classpath directory

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

    the word "path" in Java classpath contexts, particularly in copyright headers and technical documentation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    the word “path” (as in “class path”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     désactiv
    -2.03
    翆
    -2.02
    瑒
    -1.84
    𖥧
    -1.81
    ܜ
    -1.70
    栝
    -1.67
    
    -1.66
     prisa
    -1.66
    AutoModerator
    -1.65
    紱
    -1.65
    POSITIVE LOGITS
     хотела
    1.84
    eficent
    1.84
    erintah
    1.80
    很高
    1.79
    as
    1.77
     jub
    1.74
    ligators
    1.69
    d
    1.64
    的身
    1.64
     Assistant
    1.63
    Activations Density 0.004%

    No Known Activations