© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13836
    Prev
    Next
    INDEX
    Explanations

    number of characters

    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
    눙
    -1.31
    няются
    -1.31
     etre
    -1.24
     cucchiai
    -1.20
     Metode
    -1.17
    >>>>>
    -1.16
     º
    -1.13
    鐗
    -1.13
     illustratie
    -1.13
     opr
    -1.13
    POSITIVE LOGITS
    ','
    1.28
     Второй
    1.23
     вони
    1.20
    ônus
    1.18
    鈑
    1.16
     stále
    1.14
      
    1.14
    これも
    1.09
    匍
    1.09
     где
    1.09
    Activations Density 0.046%

    No Known Activations