© 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. 41168
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     pinjaman
    -1.08
    ременно
    -1.00
    ツイッター
    -0.97
    一般的
    -0.96
     kemeja
    -0.95
     encountering
    -0.94
    広く
    -0.93
    cją
    -0.93
    zzleHttp
    -0.92
    因为他
    -0.91
    POSITIVE LOGITS
     Bride
    1.00
     запол
    0.94
    Grüsse
    0.89
     replete
    0.88
    IZONT
    0.88
    オル
    0.87
    Genre
    0.85
    </sub>
    0.85
    Groetjes
    0.85
    ibid
    0.85
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.