© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109737
    Prev
    Next
    INDEX
    Explanations

    `<?php` or `php` code snippets

    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
    }:\
    -0.78
     dago
    -0.77
     духовке
    -0.75
    ετε
    -0.73
    的感觉
    -0.71
     Pfarr
    -0.71
     eternal
    -0.71
    chance
    -0.71
     hatten
    -0.70
    thren
    -0.69
    POSITIVE LOGITS
     Grit
    0.76
    Για
    0.74
     Jai
    0.74
     arreglos
    0.74
    Mission
    0.74
    onesia
    0.74
    彌
    0.73
    Год
    0.73
     bandits
    0.73
     incen
    0.72
    Activations Density 0.002%

    No Known Activations