© 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. 197900
    Prev
    Next
    INDEX
    Explanations

    money online

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

    **`Arc` and `human` language**

    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
     sales
    0.50
    !(
    0.47
     marketer
    0.46
     petani
    0.45
     pandemic
    0.44
     musician
    0.44
    д
    0.44
    ด
    0.44
     journalist
    0.43
     musicians
    0.43
    POSITIVE LOGITS
     جيد
    0.61
    所述
    0.51
     целью
    0.49
     للج
    0.48
    bmp
    0.48
     κατά
    0.47
     عليهم
    0.47
     空
    0.47
     తీ
    0.47
     ఘ
    0.47
    Activations Density 0.000%

    No Known Activations