© 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. 74712
    Prev
    Next
    INDEX
    Explanations

    introduction {#sec1} or gnu license

    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
     &
    -1.97
     a
    -1.95
    ↵
    -1.89
    ve
    -1.81
     (
    -1.80
     my
    -1.80
     them
    -1.79
    ?
    -1.78
     me
    -1.74
     Our
    -1.72
    POSITIVE LOGITS
     désert
    2.25
    </i>
    2.17
    vantaged
    2.11
    ᐕ
    1.98
    ᚹ
    1.97
     akhirnya
    1.92
     эту
    1.87
     inilah
    1.82
     cimetière
    1.81
     meriva
    1.80
    Activations Density 0.000%

    No Known Activations