© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3459
    Prev
    Next
    INDEX
    Explanations

    results and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    िस्थित
    2.82
    te
    2.78
    inness
    2.64
    ifiable
    2.60
    ոչ
    2.57
    ಿಗ
    2.51
    ि
    2.45
     Her
    2.43
    aż
    2.41
    िक
    2.38
    POSITIVE LOGITS
    ات
    2.87
    s
    2.67
    زب
    2.57
    餚
    2.41
    橇
    2.39
    от
    2.35
    দ্ম
    2.29
     ```
    2.27
    τε
    2.26
    윕
    2.26
    Activations Density 0.402%

    No Known Activations