© 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. 38720
    Prev
    Next
    INDEX
    Explanations

    creating and generating outputs

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

    generate text

    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
    irond
    0.64
    ۔
    0.63
    homogeneous
    0.60
     הג
    0.58
     homogeneous
    0.57
     workbench
    0.57
     homogenous
    0.57
    的对象
    0.56
     কাঠামো
    0.56
    о
    0.56
    POSITIVE LOGITS
     Generate
    1.15
     Generated
    1.13
     generated
    1.04
    生成
    1.01
     generates
    1.01
     Generating
    0.98
     generating
    0.96
    Generate
    0.94
     GENER
    0.94
     generate
    0.90
    Activations Density 0.020%

    No Known Activations