© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58749
    Prev
    Next
    INDEX
    Explanations

    prompting for user input

    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
     Thessalon
    -0.75
     kalender
    -0.75
     eksper
    -0.74
     Каждый
    -0.73
    kowski
    -0.73
     Ebenezer
    -0.73
    取り組み
    -0.72
     sende
    -0.71
    アプローチ
    -0.70
     داشتم
    -0.69
    POSITIVE LOGITS
     ask
    3.25
     asking
    3.25
     asks
    2.94
     asked
    2.72
     Ask
    2.61
    Ask
    2.59
    ask
    2.56
     prompt
    2.47
    asking
    2.39
    Asking
    2.38
    Activations Density 0.125%

    No Known Activations