© 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. 67298
    Prev
    Next
    INDEX
    Explanations

    needs, requirements, claims, doing, want, seed

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

    controlling behavior; cause and effect

    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
     và
    0.50
    ر
    0.49
    ר
    0.49
    н
    0.48
     Aquí
    0.47
     جنوبی
    0.47
    ન
    0.46
     ಮತ್ತು
    0.46
    Customers
    0.45
    ↵↵
    0.45
    POSITIVE LOGITS
    ků
    0.52
    краё
    0.44
    แมนเชสเตอร์ซิตี
    0.44
    hlt
    0.44
     โจทย์
    0.44
    ktional
    0.44
    ঞ্চলে
    0.43
     уроке
    0.43
     ਜਾਂ
    0.43
    ক্স
    0.43
    Activations Density 0.000%

    No Known Activations