© 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. 195715
    Prev
    Next
    INDEX
    Explanations

    propriété owners, leading brands

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

    sprinkle colors

    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
    </h2>
    0.59
    in
    0.55
    <0x0D>
    0.54
    ↵
    0.51
    su
    0.48
    nd
    0.47
     inception
    0.45
    s
    0.45
    Blueprint
    0.45
    Base
    0.44
    POSITIVE LOGITS
     propriétaire
    0.52
     negó
    0.52
     vécu
    0.52
     dirigeants
    0.52
     amoureux
    0.50
     transformada
    0.50
     souten
    0.50
     propriété
    0.50
     propriétaires
    0.49
     sabbam
    0.49
    Activations Density 0.000%

    No Known Activations