© 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. 18460
    Prev
    Next
    INDEX
    Explanations

    Esperanto plurals and compounds

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

    Esperanto language

    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
     Collectively
    0.46
     تقدر
    0.43
     ಕೂದಲ
    0.41
     প্রথমবারের
    0.41
     khoản
    0.41
    瀚
    0.40
    彪
    0.40
     cứ
    0.40
     प्रॉपर्टी
    0.40
     Rookie
    0.40
    POSITIVE LOGITS
     María
    0.57
    María
    0.54
    nombre
    0.49
     pandemia
    0.48
     inkl
    0.48
    sister
    0.48
     humbly
    0.47
     apparition
    0.47
    áme
    0.47
     exemple
    0.46
    Activations Density 0.000%

    No Known Activations