© 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. 13-GEMMASCOPE-2-RES-16K
    7. 5777
    Prev
    Next
    INDEX
    Explanations

    reach out

    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_13_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
    ρια
    2.55
    cid
    2.42
    ្រ
    2.35
     finais
    2.32
    ــــ
    2.20
    ᾗ
    2.16
    泯
    2.12
    it
    2.11
    Servlet
    2.11
    کرین
    2.10
    POSITIVE LOGITS
    veratrol
    3.16
    ष्‍ट्र
    3.10
    বীন্দ্র
    3.07
    ྫ
    3.01
    ྐ
    2.97
    ాత్రి
    2.89
    िश्वत
    2.88
    čun
    2.78
    खिक
    2.64
    বীন্দ্রনাথ
    2.61
    Activations Density 2.129%

    No Known Activations