© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 47773
    Prev
    Next
    INDEX
    Explanations

    explicit content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    0.68
    (
    0.68
    al
    0.63
    es
    0.59
    l
    0.59
    ë
    0.59
    iem
    0.58
    ت
    0.58
     il
    0.57
     nen
    0.57
    POSITIVE LOGITS
    кови
    0.58
     స్వా
    0.57
    ವಾಗಿದೆ
    0.55
    ковник
    0.54
     WARREN
    0.54
    }_{+}
    0.54
    서는
    0.53
     मुद्राओं
    0.52
    是由
    0.51
     Recht
    0.51
    Activations Density 0.197%

    No Known Activations