© 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. 91303
    Prev
    Next
    INDEX
    Explanations

    taking opportunities

    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
    inders
    -0.77
    ⏫
    -0.77
    bnb
    -0.76
    Actor
    -0.75
    πος
    -0.73
     успеха
    -0.73
    导致
    -0.71
     انجام
    -0.71
    indsay
    -0.70
    HEARING
    -0.70
    POSITIVE LOGITS
     presenting
    3.92
     presents
    3.63
     presentation
    3.56
     presented
    3.53
     Presenting
    3.09
    Presenting
    3.06
     Presentation
    3.03
    presentation
    3.00
    Presentation
    2.95
     presentations
    2.94
    Activations Density 0.100%

    No Known Activations