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. 8058
    Prev
    Next
    INDEX
    Explanations

    reminiscence activities or proper nouns

    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
     kids
    -0.83
    нымъ
    -0.80
    ged
    -0.79
    sians
    -0.78
    Efficiency
    -0.77
    zungs
    -0.77
     детской
    -0.76
     Canaria
    -0.76
    rup
    -0.76
     ны
    -0.74
    POSITIVE LOGITS
     activities
    1.42
     activity
    1.40
     reminis
    1.36
     residents
    1.23
     stimulating
    1.20
     Activities
    1.19
     Residents
    1.16
     therapeutic
    1.16
     therapy
    1.15
     stimulates
    1.14
    Activations Density 0.017%

    No Known Activations