© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 14080
    Prev
    Next
    INDEX
    Explanations

    Finnish language

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    忍
    0.61
     алы
    0.59
    ց
    0.54
    iscilla
    0.52
    တ်
    0.51
     arti
    0.50
    StringVar
    0.50
     lengan
    0.50
     cest
    0.50
     unteren
    0.50
    POSITIVE LOGITS
    ítás
    0.62
    謬
    0.61
    மைப்பு
    0.54
    umus
    0.53
    ாட்டு
    0.52
    yte
    0.52
    ்ப்பு
    0.52
    fehl
    0.52
    bey
    0.52
    вина
    0.52
    Activations Density 0.000%

    No Known Activations