© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43797
    Prev
    Next
    INDEX
    Explanations

    anniversaries, years, and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     you
    -2.00
     dorp
    -1.61
    鮰
    -1.57
     stap
    -1.54
     certaines
    -1.52
    utdown
    -1.52
    ÇÕES
    -1.52
    ophageal
    -1.52
     is
    -1.51
     latter
    -1.51
    POSITIVE LOGITS
     own
    2.34
    ",
    1.69
    </h2>
    1.67
    but
    1.66
     schlechte
    1.65
    that
    1.52
     که
    1.49
    ’,
    1.48
     begleiten
    1.45
    with
    1.44
    Activations Density 0.042%

    No Known Activations