© 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. 58405
    Prev
    Next
    INDEX
    Explanations

    Lok Sabha, Places, Regions

    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
    饹
    -2.64
     unſ
    -2.56
     bahwa
    -2.45
    ༀ
    -2.38
    唻
    -2.33
    푣
    -2.28
    瑨
    -2.19
    鸶
    -2.16
    珖
    -2.14
    they
    -2.13
    POSITIVE LOGITS
    "
    3.44
    s
    2.53
    </i>
    2.41
    ↵↵
    2.34
    <bos>
    2.27
    </sub>
    2.06
    ㈯
    2.05
     aislada
    2.00
     schwierig
    1.98
     maxim
    1.97
    Activations Density 0.003%

    No Known Activations