© 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. 13128
    Prev
    Next
    INDEX
    Explanations

    without, no, sans, bez

    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
     sicheren
    -2.42
     useAppContext
    -2.22
     schnellen
    -2.11
    懸命
    -2.03
    Уже
    -1.89
     still
    -1.89
    早已
    -1.83
    渽
    -1.80
     Preisen
    -1.80
     praktischen
    -1.77
    POSITIVE LOGITS
    когда
    1.99
     zonder
    1.92
    蹕
    1.85
     regard
    1.85
    and
    1.80
    ୩
    1.78
    🧏
    1.77
    鋱
    1.77
     fortalec
    1.76
     naturligt
    1.75
    Activations Density 0.009%

    No Known Activations