© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 130696
    Prev
    Next
    INDEX
    Explanations

    online content and products

    np_acts-logits-general · gemini-2.5-flash-lite

    concepts and their contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    喻
    0.48
    राष्ट्र
    0.46
    来自
    0.46
    Proud
    0.46
    可爱
    0.45
    現
    0.45
    房
    0.45
    融入
    0.44
    zum
    0.44
    充
    0.44
    POSITIVE LOGITS
     تھی۔
    0.48
    ،
    0.48
     réglementation
    0.47
     dakkh
    0.47
     terapi
    0.47
     menurun
    0.47
     departure
    0.46
    nya
    0.46
    postos
    0.45
     vacanam
    0.45
    Activations Density 0.001%

    No Known Activations