© 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. 159143
    Prev
    Next
    INDEX
    Explanations

    ordinal, directional, or noun followed by a descriptor

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

    transactions and debts

    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
     Nhật
    0.52
     yapıyor
    0.51
     Şubat
    0.50
    า
    0.48
    ำ
    0.47
    璁
    0.46
     yaptı
    0.45
    ї
    0.45
    ка
    0.45
    та
    0.45
    POSITIVE LOGITS
    INT
    0.49
    of
    0.45
    HIG
    0.45
    邦
    0.44
    only
    0.43
    CTIONS
    0.43
    uerte
    0.43
    POINT
    0.42
    [\
    0.42
    interactions
    0.42
    Activations Density 0.001%

    No Known Activations