© 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. 7346
    Prev
    Next
    INDEX
    Explanations

    is needed

    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
    شیر
    -1.30
     dekoratif
    -1.27
    escape
    -1.27
     occidentalis
    -1.26
    zerű
    -1.26
    Новые
    -1.25
    bró
    -1.25
     девочки
    -1.24
    ťaž
    -1.23
    script
    -1.22
    POSITIVE LOGITS
    用到
    1.61
     médicaux
    1.38
    还是要
    1.35
     mesmerizing
    1.34
     breathtaking
    1.34
    也不能
    1.34
    又在
    1.33
    はこの
    1.33
     estará
    1.32
     机械
    1.31
    Activations Density 0.066%

    No Known Activations