© 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. 12-GEMMASCOPE-2-RES-16K
    7. 183
    Prev
    Next
    INDEX
    Explanations

    idiomatic punctuation and non-Latin scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
     numerous
    0.65
     observable
    0.65
     eigenvectors
    0.63
     bequest
    0.63
    듕
    0.62
     demolished
    0.62
    ८
    0.62
    𝗥
    0.61
     dynamically
    0.60
    ἆ
    0.60
    POSITIVE LOGITS
    ર
    0.90
    ر
    0.89
    ل
    0.84
    м
    0.80
    ம்
    0.79
    ной
    0.79
    ת
    0.79
    ند
    0.76
    けた
    0.72
    ین
    0.71
    Activations Density 0.258%

    No Known Activations