© 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. 71616
    Prev
    Next
    INDEX
    Explanations

    pronouns then verbs

    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
     Some
    -1.64
     που
    -1.42
     ん
    -1.41
     Sometimes
    -1.39
    ࿚
    -1.34
    Some
    -1.32
    ("")
    -1.32
     respirar
    -1.30
    borns
    -1.29
     Mostly
    -1.28
    POSITIVE LOGITS
     of
    1.49
     marquer
    1.34
     raconter
    1.34
     indivíduos
    1.32
     områ
    1.29
     episódios
    1.29
     kuning
    1.24
    าก็
    1.23
     menawarkan
    1.22
    被他
    1.22
    Activations Density 0.065%

    No Known Activations