© 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. 102109
    Prev
    Next
    INDEX
    Explanations

    price, dissolved, vertebrae, opportunity, efforts

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

    defend his title

    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
    }{
    0.57
    > </
    0.54
    d
    0.49
    da
    0.48
    b
    0.48
    al
    0.47
    ukuran
    0.47
    hidupan
    0.47
     hendak
    0.47
    ab
    0.46
    POSITIVE LOGITS
     Joey
    0.52
    셋
    0.49
    গুলিতে
    0.49
     utilisons
    0.48
     facilite
    0.46
     CHRISTIAN
    0.45
    别人
    0.45
    ouille
    0.45
    헥
    0.45
    许
    0.44
    Activations Density 0.000%

    No Known Activations