© 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. 247287
    Prev
    Next
    INDEX
    Explanations

    business functions and operations

    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
    のお客様
    0.49
     patham
    0.47
     patted
    0.47
     clutching
    0.47
    JECT
    0.46
     explosions
    0.45
    <unused27>
    0.45
     pertanian
    0.45
     latar
    0.44
     detonations
    0.44
    POSITIVE LOGITS
     {
    0.50
       
    0.49
     সবগুলো
    0.45
      
    0.44
     ==
    0.42
    Inventory
    0.41
     foc
    0.41
     Inventory
    0.41
    ongo
    0.41
    amh
    0.41
    Activations Density 0.001%

    No Known Activations