© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59215
    Prev
    Next
    INDEX
    Explanations

    corporations and efficiency

    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
     This
    -1.45
    Only
    -1.39
    Although
    -1.28
     When
    -1.25
    This
    -1.23
    Despite
    -1.23
     Even
    -1.22
    Like
    -1.22
    Even
    -1.20
    Other
    -1.20
    POSITIVE LOGITS
    </h2>
    1.27
     corporations
    1.18
     первых
    1.14
     mooie
    1.09
     pasamos
    1.09
     gebre
    1.08
    ότε
    1.08
     totale
    1.07
     choroby
    1.07
     části
    1.06
    Activations Density 0.050%

    No Known Activations