© 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. 84549
    Prev
    Next
    INDEX
    Explanations

    code assignments or definitions

    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
     untuk
    -1.44
    せずに
    -1.40
                    
    -1.40
    To
    -1.34
    来看看
    -1.33
     семье
    -1.30
     indescri
    -1.30
    Также
    -1.27
     autorisation
    -1.27
         
    -1.26
    POSITIVE LOGITS
    uš
    1.46
    rą
    1.39
     Denken
    1.36
     Daß
    1.36
    ifikasi
    1.30
     EACH
    1.27
    orek
    1.27
    şte
    1.27
     ſame
    1.26
    哢
    1.26
    Activations Density 0.039%

    No Known Activations