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. 8339
    Prev
    Next
    INDEX
    Explanations

    months and dates

    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
     mengumumkan
    -1.01
     quelconque
    -1.00
    ñores
    -0.97
    Андрей
    -0.94
    apk
    -0.90
     съм
    -0.86
    Откры
    -0.86
    Ито
    -0.86
    Глава
    -0.86
    Що
    -0.85
    POSITIVE LOGITS
     June
    1.07
     December
    1.04
     January
    1.04
     July
    1.02
     October
    1.01
     September
    1.00
     March
    0.98
     and
    0.96
    ieu
    0.95
    /*",
    0.94
    Activations Density 0.010%

    No Known Activations