© 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. 128502
    Prev
    Next
    INDEX
    Explanations

    determiners followed by nouns/concepts

    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
     eachother
    -1.52
     خوبه
    -1.34
     zout
    -1.28
    lijken
    -1.27
     occas
    -1.24
    asilkan
    -1.21
     commences
    -1.19
    </h2>
    -1.16
    的東西
    -1.16
     it
    -1.15
    POSITIVE LOGITS
     “
    1.55
     any
    1.55
     votre
    1.31
     much
    1.29
    Your
    1.27
     Your
    1.24
    The
    1.22
     dám
    1.22
     cualquier
    1.21
     "
    1.20
    Activations Density 0.287%

    No Known Activations