© 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. 193320
    Prev
    Next
    INDEX
    Explanations

    loans, hair, levitra

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

    network topologies

    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
    垣
    0.48
    kWh
    0.47
    Calories
    0.47
     ಕಳೆದ
    0.47
    RIES
    0.47
    rā
    0.47
     kesel
    0.46
    RAY
    0.46
     tikai
    0.46
    ΙΑ
    0.45
    POSITIVE LOGITS
    ↵↵↵
    0.50
    ↵
    0.48
                         
    0.47
     Steven
    0.46
     on
    0.46
     /
    0.45
      
    0.44
     delegations
    0.44
     running
    0.44
     Phil
    0.43
    Activations Density 0.000%

    No Known Activations