© 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. 95068
    Prev
    Next
    INDEX
    Explanations

    Lawrence of Arabia; domain names

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

    best, exactly

    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
    嗲
    0.48
     dazu
    0.47
     dlg
    0.45
     vào
    0.44
     bao
    0.44
     Parte
    0.44
    يمة
    0.43
    走了
    0.43
     zu
    0.42
     carga
    0.42
    POSITIVE LOGITS
     needing
    0.54
     brushing
    0.51
     乾燥
    0.50
     eyeballs
    0.49
    ()}')
    0.48
     tenacious
    0.48
     arranging
    0.47
     invariance
    0.47
     perfecting
    0.47
     inviol
    0.47
    Activations Density 0.000%

    No Known Activations