© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123517
    Prev
    Next
    INDEX
    Explanations

    Herein we describe

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

    The word "Herein" at the beginning of a sentence, particularly in scientific or academic writing.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Conversely
    -1.96
     Notwithstanding
    -1.83
     For
    -1.73
     haughty
    -1.68
     Both
    -1.67
     расте
    -1.66
    <td>
    -1.65
     convivial
    -1.61
    )$.
    -1.58
     préciser
    -1.58
    POSITIVE LOGITS
    this
    2.05
    there
    1.99
    寕
    1.93
    which
    1.89
     calientes
    1.87
    even
    1.86
    嵛
    1.86
     abiye
    1.84
    ergies
    1.83
    being
    1.81
    Activations Density 0.016%

    No Known Activations