© 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. 73737
    Prev
    Next
    INDEX
    Explanations

    events, weeks, and meetings

    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
    [
    -1.46
     if
    -1.36
    粉色
    -1.30
     PLEASE
    -1.27
     vorhandenen
    -1.26
     heutige
    -1.26
     wymaga
    -1.22
     です
    -1.21
     devices
    -1.21
     damaligen
    -1.20
    POSITIVE LOGITS
    метр
    1.45
    🫓
    1.30
     Autres
    1.30
     Entdecke
    1.29
     reír
    1.26
     hés
    1.25
    Bigr
    1.24
    錀
    1.23
     méd
    1.23
     ruptura
    1.19
    Activations Density 0.040%

    No Known Activations