© 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. 160930
    Prev
    Next
    INDEX
    Explanations

    Prada, Adidas, K

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

    specific context

    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
    2
    0.50
    cciones
    0.47
    تان
    0.46
     Descent
    0.45
     trás
    0.43
    ributions
    0.43
    LayoutParams
    0.42
     Packed
    0.42
    巒
    0.42
    3
    0.42
    POSITIVE LOGITS
     immunoglobulin
    0.59
     Kalam
    0.52
     dibut
    0.52
     dinosaurs
    0.51
     kalam
    0.51
     hazelnuts
    0.51
     potash
    0.50
     MSU
    0.49
     worms
    0.47
     utter
    0.47
    Activations Density 0.000%

    No Known Activations