© 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. 34-GEMMASCOPE-RES-131K
    7. 77720
    Prev
    Next
    INDEX
    Explanations

    events and outcomes after 'the'

    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
    -1.27
    えたら
    -1.12
     {
    -1.09
     });
    -1.05
     девочка
    -1.04
     tjen
    -1.04
     Commandments
    -1.03
     citado
    -1.02
     refroidissement
    -1.01
    НИМА
    -1.01
    POSITIVE LOGITS
     announcement
    2.00
     decision
    1.99
     release
    1.85
     appointment
    1.85
     arrival
    1.79
     ongoing
    1.69
     results
    1.65
     arrest
    1.63
     outcome
    1.62
     signing
    1.60
    Activations Density 0.115%

    No Known Activations