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. 131
    Prev
    Next
    INDEX
    Explanations

    programming code and technical terms

    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
     tho
    -0.83
    ܣ
    -0.83
     fila
    -0.78
    噂
    -0.76
    如有
    -0.74
    verdad
    -0.73
     confronto
    -0.73
    sr
    -0.73
    PRF
    -0.69
    懺
    -0.68
    POSITIVE LOGITS
     سوی
    0.96
     totes
    0.94
    胛
    0.82
     definitiv
    0.80
     delà
    0.79
    onner
    0.78
     triathlon
    0.77
     gage
    0.76
     culoare
    0.75
     umsch
    0.75
    Activations Density 0.022%

    No Known Activations