© 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. 15193
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

    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
     and
    -2.16
     таком
    -1.30
    ០
    -1.28
     exámenes
    -1.27
    ợp
    -1.27
    upiter
    -1.27
    龊
    -1.23
    interopRequire
    -1.22
    
    -1.21
    IKO
    -1.20
    POSITIVE LOGITS
     других
    1.48
     there
    1.48
    autres
    1.35
     is
    1.35
    新的
    1.30
     abbiamo
    1.25
    其他
    1.24
     servire
    1.20
     racconta
    1.20
     Selain
    1.17
    Activations Density 0.102%

    No Known Activations