© 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. 223667
    Prev
    Next
    INDEX
    Explanations

    worst outcome, modest increase

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

    trained by Google DeepMind

    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
     fourteenth
    0.62
     thirteenth
    0.55
    闻
    0.49
    liš
    0.47
    ojen
    0.46
     fifteenth
    0.46
    铁路
    0.46
    恹
    0.46
     railroads
    0.45
     twelfth
    0.44
    POSITIVE LOGITS
    প্রতি
    0.44
     Alex
    0.43
     Workbench
    0.42
     EventHandler
    0.42
    ERGY
    0.42
    পাত
    0.41
     Manuel
    0.41
    contrast
    0.41
     Michael
    0.40
    Alex
    0.40
    Activations Density 0.000%

    No Known Activations