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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38796
    Prev
    Next
    INDEX
    Explanations

    starts, começo, begin, iniciar

    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
    栳
    -2.95
    <
    -2.83
    них
    -2.31
    but
    -2.31
     この
    -2.27
    枼
    -2.22
    身上的
    -2.11
     réduit
    -2.09
     あ
    -1.98
     nemen
    -1.96
    POSITIVE LOGITS
    ﹔
    2.22
    ']
    2.13
    ()))
    2.11
    苼
    1.98
     Some
    1.97
    。）
    1.96
     手機
    1.93
    на
    1.93
    禤
    1.92
    ()]
    1.91
    Activations Density 0.002%

    No Known Activations