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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 859
    Prev
    Next
    INDEX
    Explanations

    sounds perfect

    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
     ロック
    -1.38
     your
    -1.28
    ");
    -1.22
    いま
    -1.22
    궈
    -1.21
    </tr>
    -1.19
    instancetype
    -1.16
     saranno
    -1.15
    èvement
    -1.14
    ---
    -1.13
    POSITIVE LOGITS
     varias
    1.40
     varios
    1.22
     TAMBIÉN
    1.21
    ઁ
    1.17
    找到了
    1.17
     would
    1.15
     questioned
    1.14
    劻
    1.13
    ublik
    1.13
    
    1.13
    Activations Density 0.195%

    No Known Activations