© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1731
    Prev
    Next
    INDEX
    Explanations

    Estonian words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     একটু
    0.94
    それ
    0.88
     それ
    0.86
    墺
    0.82
     dowol
    0.79
     opět
    0.78
     йо
    0.77
    ஷன்
    0.77
     ウェ
    0.76
     알
    0.76
    POSITIVE LOGITS
     või
    1.29
     võ
    1.27
     mõ
    1.24
     tõ
    1.24
     ning
    1.24
     õ
    1.24
    õ
    1.24
     lõ
    1.23
     põ
    1.22
     korral
    1.22
    Activations Density 0.018%

    No Known Activations