© 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. 37275
    Prev
    Next
    INDEX
    Explanations

    multi-lingual concepts

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

    for now

    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
    ოველ
    0.43
    OLI
    0.42
     Luxe
    0.42
    kins
    0.41
    伨
    0.40
     نوفمبر
    0.38
    承
    0.38
    月初
    0.38
    డింది
    0.37
    Ｏ
    0.37
    POSITIVE LOGITS
     bolsillo
    0.50
     всегда
    0.48
     utilisée
    0.47
     Kraken
    0.46
     همیشه
    0.45
     dř
    0.45
     барои
    0.45
     celtic
    0.45
     gdzie
    0.45
    奀
    0.44
    Activations Density 0.001%

    No Known Activations