© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13452
    Prev
    Next
    INDEX
    Explanations

    collocations and foreign words

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

    Cole, admin, Art, French, 5

    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_16k_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
    Balls
    0.49
    들
    0.42
    ᱴ
    0.42
    며
    0.41
    Punk
    0.41
    이나
    0.40
    WR
    0.40
    Tw
    0.40
    8
    0.40
     पांडे
    0.40
    POSITIVE LOGITS
     മന്ത്രി
    0.55
     kommen
    0.54
    ချင်း
    0.54
     kommt
    0.53
    ক্ষেত্র
    0.52
     hastalık
    0.51
     primul
    0.49
     ısı
    0.48
     tür
    0.48
    ümüş
    0.48
    Activations Density 0.622%

    No Known Activations