© 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. 126215
    Prev
    Next
    INDEX
    Explanations

    depend on

    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
    ↵↵
    0.53
    I
    0.52
    Vale
    0.49
    5
    0.46
    ↵
    0.46
    є
    0.46
    7
    0.46
    </b>
    0.45
    Colombia
    0.45
    Administration
    0.45
    POSITIVE LOGITS
     quadruple
    0.50
    ্ব
    0.46
     développ
    0.45
    ettha
    0.45
     ܠ
    0.45
     indigenous
    0.45
    墘
    0.45
     définit
    0.44
    uous
    0.43
     déclar
    0.43
    Activations Density 0.003%

    No Known Activations