© 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. 34-GEMMASCOPE-RES-131K
    7. 83439
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by 'bring' or 'offer'

    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_34/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
    ções
    -0.85
    prende
    -0.77
    vada
    -0.77
     derer
    -0.75
    chov
    -0.75
    InetAddress
    -0.75
    んこ
    -0.75
     говорится
    -0.73
    breviations
    -0.73
    [:,:,
    -0.73
    POSITIVE LOGITS
     bring
    4.44
     brings
    4.22
    Bring
    3.92
     Bring
    3.64
    bring
    3.61
     bringing
    3.53
    Bringing
    3.23
     Brings
    3.02
    bringing
    2.95
     BRING
    2.94
    Activations Density 0.047%

    No Known Activations