© 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. 92048
    Prev
    Next
    INDEX
    Explanations

    Tag Challenge, Summer Flowers, Current 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
    佟
    -0.94
     reinstalling
    -0.83
     pastors
    -0.82
    幻想
    -0.81
     nahezu
    -0.80
     supremely
    -0.78
     virtually
    -0.78
    Epis
    -0.76
    ēja
    -0.76
     cleverly
    -0.75
    POSITIVE LOGITS
     dè
    0.87
     complica
    0.85
     madera
    0.83
    GMT
    0.81
     GMT
    0.80
     sviluppo
    0.78
     doy
    0.77
    一旁
    0.77
     arriver
    0.76
    tting
    0.76
    Activations Density 0.008%

    No Known Activations