© 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. 102766
    Prev
    Next
    INDEX
    Explanations

    Garcia

    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
     wayward
    -2.67
     作る
    -2.59
    过后
    -2.59
    图为
    -2.55
     یا
    -2.48
    最后由
    -2.45
     dizzy
    -2.45
     новая
    -2.41
     我们
    -2.39
    阋
    -2.38
    POSITIVE LOGITS
    衚
    2.98
    .
    2.86
     ساعد
    2.44
     hän
    2.39
    ほうが
    2.34
    actéristi
    2.30
     kepada
    2.13
     môžete
    2.11
    iſter
    2.08
    攥
    2.08
    Activations Density 0.002%

    No Known Activations