© 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. 8890
    Prev
    Next
    INDEX
    Explanations

    words following possessive 's

    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
    There
    -2.44
     Because
    -2.39
     Even
    -2.27
    Even
    -2.25
     there
    -2.25
     should
    -2.25
     even
    -2.22
     if
    -2.19
     When
    -2.19
     one
    -2.14
    POSITIVE LOGITS
     diamants
    2.17
     pertes
    2.09
     Dinas
    2.09
     gouttes
    2.08
     rigue
    2.08
     magnific
    2.05
     deliciously
    2.03
     delightfully
    2.02
     wonderfully
    1.97
     incredibly
    1.96
    Activations Density 0.061%

    No Known Activations