© 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. 116786
    Prev
    Next
    INDEX
    Explanations

    Divorce, rentals, or DOL

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

    leads generated

    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
     vaccines
    0.43
     recesses
    0.42
    తల
    0.42
    यॉर्क
    0.41
    ˗
    0.41
    <unused100>
    0.40
     lily
    0.40
    र्थिक
    0.39
    
    0.39
     سالب
    0.39
    POSITIVE LOGITS
     Environments
    0.45
     Operational
    0.45
     लिये
    0.44
     Interactive
    0.44
     oid
    0.43
     Divorce
    0.43
     Help
    0.42
    विण्यासाठी
    0.42
     II
    0.42
     Hilfe
    0.42
    Activations Density 0.001%

    No Known Activations