© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11263
    Prev
    Next
    INDEX
    Explanations

    UA ‘

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

    Urano, Saturno, Júpiter, Marte

    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_40_width_16k_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
    grado
    0.44
     যাহা
    0.42
     ravaged
    0.42
    ĺ
    0.41
    GRO
    0.41
    mejor
    0.40
    rique
    0.40
    poste
    0.39
     sord
    0.39
     warrants
    0.39
    POSITIVE LOGITS
     UU
    0.61
     uu
    0.57
     UM
    0.56
     UF
    0.56
     UH
    0.53
     UB
    0.53
     U
    0.52
     Uw
    0.51
     อุ
    0.51
     UC
    0.50
    Activations Density 0.208%

    No Known Activations