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. 107
    Prev
    Next
    INDEX
    Explanations

    parsing and testing strings

    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
     bajo
    -0.76
    客人
    -0.75
     current
    -0.74
    ervos
    -0.74
    ogical
    -0.74
     अच्छ
    -0.72
     örgü
    -0.72
    rots
    -0.71
     proposals
    -0.71
    dication
    -0.70
    POSITIVE LOGITS
     from
    0.97
     fabriquer
    0.82
     Rend
    0.81
    مقال
    0.81
    рованы
    0.81
    槎
    0.81
     丼
    0.80
    Музыка
    0.79
     alltså
    0.79
    parse
    0.78
    Activations Density 0.021%

    No Known Activations