© 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. 104592
    Prev
    Next
    INDEX
    Explanations

    best effort

    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
            
    -1.29
     It
    -1.27
    فين
    -1.27
     эффективность
    -1.23
     Lexikon
    -1.23
    engertian
    -1.21
    Hozzáférés
    -1.21
     Why
    -1.20
     Compared
    -1.20
    awsze
    -1.19
    POSITIVE LOGITS
     "¡
    1.30
     -"
    1.29
     to
    1.27
    1
    1.27
    自己在
    1.25
     ザ
    1.24
     ۱۱
    1.23
    8
    1.20
    ומת
    1.19
    -"
    1.18
    Activations Density 0.007%

    No Known Activations