© 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. 223284
    Prev
    Next
    INDEX
    Explanations

    finding or submitting requests

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

    template, example, framework

    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
    aver
    0.50
     tige
    0.47
     nursing
    0.46
    aga
    0.46
    ach
    0.46
    apy
    0.45
    å
    0.44
    aft
    0.43
     NFL
    0.43
     saker
    0.43
    POSITIVE LOGITS
     ننوت
    0.57
     Hochzeit
    0.51
    ၅
    0.50
    Diese
    0.50
    Scholar
    0.49
    نې
    0.49
    सीएल
    0.48
     Antrag
    0.47
    tìm
    0.47
    pedido
    0.47
    Activations Density 0.000%

    No Known Activations