© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13285
    Prev
    Next
    INDEX
    Explanations

    BroadcastReceiver

    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
     ultimi
    -1.66
    韬
    -1.45
     nocturna
    -1.41
     навыки
    -1.41
     muszą
    -1.41
     one
    -1.40
     convencer
    -1.38
     usadas
    -1.38
    .
    -1.38
     一个
    -1.36
    POSITIVE LOGITS
    錞
    1.70
     瓜
    1.51
    鉏
    1.48
    おすすめの
    1.44
    </td>
    1.40
    帮你
    1.39
    Rispondi
    1.39
    ̖
    1.37
     století
    1.36
    テキ
    1.34
    Activations Density 0.009%

    No Known Activations