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. 8044
    Prev
    Next
    INDEX
    Explanations

    Backgrounds and questions

    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
    Utah
    -0.85
     Bayern
    -0.85
    ữu
    -0.79
    verhält
    -0.79
    🐌
    -0.75
     android
    -0.75
    ската
    -0.75
    verhältnisse
    -0.75
     Fiorentina
    -0.73
     Genesee
    -0.73
    POSITIVE LOGITS
     Ngb
    1.17
    صیل
    0.82
    Shack
    0.78
     McG
    0.78
    ględ
    0.77
     Vikipedi
    0.75
     dismiss
    0.75
    ским
    0.73
     justify
    0.73
    Forsch
    0.73
    Activations Density 0.008%

    No Known Activations