© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22353
    Prev
    Next
    INDEX
    Explanations

    multilingual context or diverse languages

    np_acts-logits-general · gemini-2.5-flash-lite

    open-weights model availability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    도
    0.40
    াই
    0.38
    新闻
    0.38
    λι
    0.38
    听
    0.37
    扩散
    0.37
    悶
    0.37
    лец
    0.36
     lớn
    0.36
     BIG
    0.36
    POSITIVE LOGITS
     Mycobacterium
    0.56
     sowohl
    0.50
     hematopoietic
    0.49
     sacer
    0.49
    っており
    0.46
     Mannschaft
    0.46
     بحيث
    0.46
     ،
    0.45
     számára
    0.45
     uten
    0.45
    Activations Density 0.000%

    No Known Activations