© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 174767
    Prev
    Next
    INDEX
    Explanations

    instruction added

    np_acts-logits-general · gemini-2.5-flash-lite

    handle this, power, immense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     项
    0.50
     ற
    0.47
     Rä
    0.46
     フォー
    0.43
    hra
    0.42
     gripe
    0.42
    ストラ
    0.42
    ிட்ட
    0.41
     沙
    0.40
     adapté
    0.40
    POSITIVE LOGITS
    黟
    0.49
     speeds
    0.47
     disconnecting
    0.44
    রাজন
    0.44
    Chloe
    0.44
     coverings
    0.43
    Whoever
    0.42
     Networks
    0.42
     تباہ
    0.42
     testim
    0.41
    Activations Density 0.000%

    No Known Activations