© 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. 154436
    Prev
    Next
    INDEX
    Explanations

    save our

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

    differential diagnoses

    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
    ↵
    0.60
     Lucien
    0.50
    Nada
    0.47
     rap
    0.42
    ↵↵↵
    0.42
     Raton
    0.41
    Mate
    0.41
    Agreement
    0.41
    grand
    0.41
     progreso
    0.41
    POSITIVE LOGITS
    ські
    0.52
    不支持
    0.52
     പിന്തുണ
    0.52
     ஆண்டுகள்
    0.52
     वर्षों
    0.50
    ᔨ
    0.50
    重複
    0.49
     anguish
    0.49
    嶆
    0.48
    rentices
    0.48
    Activations Density 0.000%

    No Known Activations