© 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. 227324
    Prev
    Next
    INDEX
    Explanations

    foreign words and proper nouns

    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
     cultivate
    0.49
     nad
    0.48
    AvlTree
    0.47
    苙
    0.46
     kan
    0.46
     consider
    0.46
    یە
    0.46
     Filho
    0.45
    鼬
    0.45
    并不是
    0.44
    POSITIVE LOGITS
    าร์
    0.55
    ンテ
    0.47
    Requ
    0.45
    करार
    0.45
    version
    0.44
    quare
    0.44
     뭐가
    0.43
    ovou
    0.42
    PAY
    0.42
    ровала
    0.42
    Activations Density 0.001%

    No Known Activations