© 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. 128873
    Prev
    Next
    INDEX
    Explanations

    numbers with separators

    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
     Other
    -1.37
     BigNumber
    -1.22
     a
    -1.20
     станет
    -1.20
     Another
    -1.18
    ים
    -1.17
     Дру
    -1.16
     Sahne
    -1.15
    ība
    -1.15
     其他
    -1.14
    POSITIVE LOGITS
     of
    2.78
    6
    1.64
     nowego
    1.59
    
    1.52
    3
    1.48
     ogranic
    1.45
    ンの
    1.38
     posibles
    1.37
     neues
    1.36
    8
    1.34
    Activations Density 0.020%

    No Known Activations