© 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. 244031
    Prev
    Next
    INDEX
    Explanations

    financial savings and discounts

    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
    萨
    0.46
    女
    0.46
     nữ
    0.45
    ፔ
    0.45
    廾
    0.44
    ױ
    0.42
     nő
    0.42
     precluded
    0.42
    뿡
    0.41
    伊
    0.41
    POSITIVE LOGITS
    ona
    0.56
    ai
    0.51
    fy
    0.51
    fron
    0.50
    awa
    0.49
    aminen
    0.49
     Qar
    0.49
    apan
    0.49
    apy
    0.49
    UE
    0.49
    Activations Density 0.001%

    No Known Activations