© 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. 67324
    Prev
    Next
    INDEX
    Explanations

    Russian word beginnings and English introductory terms

    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
    踽
    -2.45
     eſſ
    -2.30
    媄
    -2.16
    裃
    -2.14
    摃
    -2.14
    ഀ
    -2.11
    に似
    -2.09
     rana
    -2.09
    谖
    -2.08
    很多的
    -2.00
    POSITIVE LOGITS
    '
    2.78
    荩
    2.14
    ↵↵
    2.06
    </b>
    2.05
     is
    1.88
    Alamat
    1.85
    <b>
    1.80
    <i>
    1.77
    
    1.74
     has
    1.73
    Activations Density 0.024%

    No Known Activations