© 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. 98636
    Prev
    Next
    INDEX
    Explanations

    As followed by pronouns

    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
     וכן
    -1.34
     what
    -1.28
    ouncements
    -1.19
    我们是
    -1.12
     and
    -1.10
     pájaro
    -1.09
    年から
    -1.06
     a
    -1.06
    ッテリー
    -1.05
    であり
    -1.03
    POSITIVE LOGITS
     he
    1.20
     they
    1.09
    ◆◆
    1.03
     you
    1.03
     the
    1.02
    SaveChangesAsync
    1.01
    inheritDoc
    1.01
    
    1.00
    providedIn
    0.98
     she
    0.96
    Activations Density 0.012%

    No Known Activations