© 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. 112552
    Prev
    Next
    INDEX
    Explanations

    cycling results and rankings

    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
     your
    -1.73
     Theologie
    -1.55
     Geistes
    -1.54
     chré
    -1.46
    这本书
    -1.43
    pæ
    -1.42
     дѣ
    -1.41
    ֠
    -1.40
     bobina
    -1.40
    貼り
    -1.40
    POSITIVE LOGITS
     verhind
    1.43
     informó
    1.38
     fhall
    1.38
     kesim
    1.36
     gjelder
    1.35
    Doktor
    1.31
     confirmó
    1.30
    
    1.26
    خره
    1.26
     parç
    1.24
    Activations Density 0.049%

    No Known Activations