© 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. 28283
    Prev
    Next
    INDEX
    Explanations

    conclusion or transition

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

    therefore, then, or thus

    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
    .
    0.51
     more
    0.50
    ”
    0.44
    ....
    0.43
     focus
    0.43
    …
    0.42
    0.41
     rohkem
    0.40
     “
    0.40
     MORE
    0.38
    POSITIVE LOGITS
     thereupon
    0.71
     therefore
    0.68
     azonban
    0.66
    therefore
    0.62
     zatem
    0.61
     daarbij
    0.61
     więc
    0.58
     tuttavia
    0.57
     pertanto
    0.57
     quindi
    0.57
    Activations Density 0.007%

    No Known Activations