© 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. 120077
    Prev
    Next
    INDEX
    Explanations

    conclusion, duration, or existence

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

    explaining concepts and connections

    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
    昭和
    0.46
     semasa
    0.46
    Პ
    0.44
    平和
    0.41
    和平
    0.41
     미래
    0.41
    ።
    0.41
    ังหวัด
    0.40
    
    0.40
     subcontract
    0.39
    POSITIVE LOGITS
     dunque
    0.42
     toujours
    0.42
     প্রশ্ন
    0.42
     Fatigue
    0.41
    なのです
    0.41
     Levin
    0.41
     প্রথমেই
    0.41
     question
    0.41
     arrêt
    0.40
     þei
    0.39
    Activations Density 0.001%

    No Known Activations