© 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. 22-GEMMASCOPE-RES-131K
    7. 25823
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by 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_22/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
     an
    -1.30
    となり
    -1.20
     our
    -1.18
     my
    -1.13
     at
    -1.09
    tonsoft
    -1.09
    ização
    -1.07
     Providing
    -1.05
     any
    -1.05
     jūs
    -1.05
    POSITIVE LOGITS
     it
    2.78
    把它
    2.30
     them
    2.02
     इसे
    1.77
    将其
    1.73
     they
    1.45
    它是
    1.41
    它
    1.41
    它们
    1.30
     use
    1.25
    Activations Density 0.098%

    No Known Activations