© 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. 148960
    Prev
    Next
    INDEX
    Explanations

    clearly works, online banking, indirect quotation

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

    relations and data points

    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
     transportasi
    0.50
     valleys
    0.46
    ဲ
    0.46
     berbagai
    0.44
     banyaknya
    0.44
    墾
    0.43
     permainan
    0.43
     estuaries
    0.42
    Dalam
    0.42
    मपुर
    0.42
    POSITIVE LOGITS
    evich
    0.47
    t
    0.43
     отношения
    0.43
    实现
    0.41
    chn
    0.41
    sch
    0.41
    窒
    0.40
     لاحظوا
    0.40
    អ្វី
    0.39
    tx
    0.39
    Activations Density 0.000%

    No Known Activations