© 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. 3032
    Prev
    Next
    INDEX
    Explanations

    I'm Gemma

    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
    nych
    3.25
    ning
    3.07
    daction
    2.98
    ष्ठी
    2.88
    বিষ্ট
    2.81
    ```
    2.71
    ところに
    2.56
    слови
    2.55
    cf
    2.51
    넉
    2.50
    POSITIVE LOGITS
    𝘩
    3.03
    𝘶
    2.98
    ゙
    2.93
    𝑢
    2.76
    ेट
    2.60
     hvert
    2.59
    IVATE
    2.59
    ivating
    2.52
    𝑜
    2.50
     regia
    2.50
    Activations Density 0.109%

    No Known Activations