© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 55094
    Prev
    Next
    INDEX
    Explanations

    explaining *why*

    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
    俨
    0.56
    стіше
    0.54
    نی
    0.51
    ênio
    0.49
    और
    0.49
    柔软
    0.49
    ừ
    0.49
    muş
    0.48
    ჰ
    0.48
    ômes
    0.48
    POSITIVE LOGITS
     size
    0.63
     rate
    0.59
    ↵
    0.58
     value
    0.55
     numerator
    0.54
     length
    0.51
     range
    0.51
     verifiable
    0.51
     intermediate
    0.50
     quantitative
    0.49
    Activations Density 0.003%

    No Known Activations