© 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. 17320
    Prev
    Next
    INDEX
    Explanations

    or / and

    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
     például
    0.44
     zejména
    0.42
     puisque
    0.41
    Таким
    0.40
    <unused1050>
    0.40
    Specifically
    0.40
     puisqu
    0.40
    РА
    0.39
    可谓
    0.39
    특히
    0.39
    POSITIVE LOGITS
     or
    0.72
    或
    0.63
     and
    0.55
     oder
    0.54
     nebo
    0.54
     veya
    0.54
     atau
    0.53
     same
    0.52
     или
    0.52
     hoặc
    0.52
    Activations Density 0.006%

    No Known Activations