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. 153
    Prev
    Next
    INDEX
    Explanations

    date or time stamps

    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
     will
    -1.42
     so
    -1.25
     for
    -1.07
     usually
    -0.99
     which
    -0.99
     on
    -0.98
     or
    -0.92
    !!!!!
    -0.89
     over
    -0.89
     four
    -0.87
    POSITIVE LOGITS
    プラスチック
    1.14
    もとも
    1.10
     SINCE
    1.05
    當然
    1.03
     calitate
    1.02
    Andere
    1.02
     recentemente
    1.02
     havet
    1.02
    誒
    1.01
     opérateur
    1.00
    Activations Density 0.016%

    No Known Activations