© 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. 10-GEMMASCOPE-RES-131K
    7. 551
    Prev
    Next
    INDEX
    Explanations

    companies 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_10/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
    1
    -2.95
    '
    -2.77
    2
    -2.72
    as
    -2.58
     sebagainya
    -2.56
     "
    -2.48
    "
    -2.47
    </h3>
    -2.44
    </u>
    -2.42
     Многие
    -2.42
    POSITIVE LOGITS
    {
    3.56
    孓
    2.80
    聍
    2.75
     всѣ
    2.64
    哢
    2.61
    另一种
    2.47
    闳
    2.45
    英寸
    2.44
    ってこと
    2.44
    ização
    2.42
    Activations Density 0.002%

    No Known Activations