© 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. 84764
    Prev
    Next
    INDEX
    Explanations

    divider and listview

    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
    Ꮟ
    -2.33
    第七
    -2.31
    שלום
    -2.23
    אין
    -2.22
     undeniably
    -2.19
    1
    -2.19
     gewiß
    -2.14
    there
    -2.11
    Для
    -2.08
    隄
    -2.08
    POSITIVE LOGITS
     "
    2.63
    蠖
    2.56
     THESE
    2.38
    赑
    2.38
    </th>
    2.36
    到时候
    2.30
    怎么能
    2.28
            
    2.23
     nasceu
    2.23
    以外の
    2.22
    Activations Density 0.001%

    No Known Activations