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. 193
    Prev
    Next
    INDEX
    Explanations

    records of scores or numbers

    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
     sign
    -1.20
     signing
    -1.15
     Sign
    -1.11
    Sign
    -1.11
     only
    -0.99
     chose
    -0.92
     signed
    -0.91
    サイン
    -0.86
     Only
    -0.86
    签
    -0.85
    POSITIVE LOGITS
     monstruos
    1.05
    
    1.00
     superhuman
    0.98
     nudo
    0.98
    artements
    0.96
    brechen
    0.94
     voul
    0.94
     hoge
    0.93
    üstü
    0.93
    REME
    0.92
    Activations Density 0.044%

    No Known Activations