© 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. 236693
    Prev
    Next
    INDEX
    Explanations

    title loan

    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
    认定
    0.50
     separación
    0.48
     calificación
    0.47
    ঙ্গের
    0.44
    缎
    0.44
    راع
    0.43
     conversación
    0.43
    行业
    0.43
    קת
    0.43
    访
    0.43
    POSITIVE LOGITS
     Schritt
    0.52
     Гор
    0.49
     Fokker
    0.48
     Gonzaga
    0.48
     Giorgio
    0.48
     Dijk
    0.47
     चंद्रशेखर
    0.47
     Dann
    0.46
     Starr
    0.46
     laugh
    0.46
    Activations Density 0.000%

    No Known Activations