© 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. 117
    Prev
    Next
    INDEX
    Explanations

    ```

    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
    𝐓
    0.96
     and
    0.93
    رى
    0.93
     altitudes
    0.86
    larından
    0.86
     enveloped
    0.86
    hitung
    0.84
    ಯಲ್ಲಿ
    0.81
    களை
    0.76
    கள்
    0.75
    POSITIVE LOGITS
    ir
    1.69
    ak
    1.55
    ia
    1.39
    り
    1.39
    ே
    1.38
    та
    1.35
    am
    1.34
    ু
    1.34
    ون
    1.31
    ad
    1.30
    Activations Density 0.011%

    No Known Activations