Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93
    Prev
    Next
    INDEX
    Explanations

    << operator on streams

    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_34/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
    できました
    -0.84
    mpro
    -0.81
     cómoda
    -0.81
    したもの
    -0.81
     מל
    -0.81
    три
    -0.81
     frantic
    -0.80
    ningarna
    -0.79
     Binnen
    -0.79
     this
    -0.78
    POSITIVE LOGITS
     <<
    0.99
    particularly
    0.88
    ักษ
    0.82
    ontes
    0.81
     possi
    0.81
     strate
    0.81
     Bucking
    0.78
     cask
    0.78
    possible
    0.77
     ダ
    0.77
    Activations Density 0.001%

    No Known Activations