© 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. 9431
    Prev
    Next
    INDEX
    Explanations

    pronoun subjects followed by auxiliary 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
    логические
    -1.35
     NIGERIA
    -1.26
    จึง
    -1.20
     asseg
    -1.20
     assortment
    -1.16
     svou
    -1.15
    ᅠ
    -1.14
    TRANSLATE
    -1.13
    ﾁ
    -1.12
    とはいえ
    -1.10
    POSITIVE LOGITS
     kind
    2.05
     really
    1.89
     kinda
    1.67
     what
    1.58
     basically
    1.57
     I
    1.54
     sort
    1.53
     there
    1.52
     actually
    1.48
     maybe
    1.45
    Activations Density 0.008%

    No Known Activations