© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40
    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
    ỗi
    -1.20
    쾰
    -1.12
     також
    -1.12
    ítése
    -1.09
     επίσης
    -1.08
    リニューアル
    -1.08
     modifi
    -1.06
     modif
    -1.06
     refe
    -1.06
    rabh
    -1.05
    POSITIVE LOGITS
     kind
    1.52
     there
    1.39
     you
    1.38
     really
    1.37
     actually
    1.34
     we
    1.34
     going
    1.33
     say
    1.30
     they
    1.25
     somebody
    1.25
    Activations Density 0.017%

    No Known Activations