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. 8379
    Prev
    Next
    INDEX
    Explanations

    license.txt or copyright.txt

    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
    gaf
    -0.75
    kız
    -0.70
    julio
    -0.69
    ئر
    -0.68
    뱃
    -0.67
    
    -0.67
     ABO
    -0.66
     mají
    -0.66
    erequisites
    -0.66
     pictograms
    -0.65
    POSITIVE LOGITS
     getaway
    0.71
     मी
    0.70
    heta
    0.68
     Wednesday
    0.66
     gest
    0.66
    华为
    0.66
    ropic
    0.65
    的行为
    0.65
     ح
    0.65
     Moz
    0.65
    Activations Density 0.061%

    No Known Activations