© 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. 10615
    Prev
    Next
    INDEX
    Explanations

    so, therefore, thus

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

    consequential "so" or "therefore"

    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
    /*.
    0.38
    <0xA2>
    0.36
     نظم
    0.36
    வதும்
    0.35
     Trên
    0.35
    㥽
    0.35
    সর
    0.35
    外部
    0.35
     செய்யப்பட்டது
    0.35
    隀
    0.35
    POSITIVE LOGITS
    所以
    2.28
     поэтому
    2.23
     nên
    2.19
    所以在
    2.19
     所以
    2.14
     więc
    2.09
    所以我
    2.06
    ですので
    2.05
    なので
    2.03
    だったので
    1.98
    Activations Density 0.254%

    No Known Activations