© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71820
    Prev
    Next
    INDEX
    Explanations

    end of code blocks

    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_31_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
    xon
    0.41
     wyb
    0.41
    ***",
    0.38
    ▬
    0.38
     जप
    0.38
    leness
    0.37
    羁
    0.37
    jons
    0.37
    eningrad
    0.37
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.37
    POSITIVE LOGITS
    న
    0.42
    DOMAIN
    0.41
    ン
    0.41
    ల
    0.39
    圓
    0.39
    ጠ
    0.39
    н
    0.39
     фи
    0.38
    ﾅ
    0.38
    ור
    0.38
    Activations Density 0.001%

    No Known Activations