© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 20870
    Prev
    Next
    INDEX
    Explanations

    common compound words and phrases

    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
     and
    -2.53
    .")
    -2.38
     '
    -2.19
    </em>
    -2.09
    dicional
    -2.02
    </h2>
    -1.89
    \"
    -1.88
    都不能
    -1.87
     ")
    -1.85
     to
    -1.80
    POSITIVE LOGITS
    ’,
    2.23
    Many
    2.22
    ’
    2.19
    Having
    2.09
    Several
    2.08
    Following
    2.03
    Being
    1.96
    ’,
    1.95
     sixteen
    1.93
    Often
    1.89
    Activations Density 2.098%

    No Known Activations