© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2321
    Prev
    Next
    INDEX
    Explanations

    charging infrastructure

    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
     ràng
    2.30
    ろん
    2.29
    အချိန်
    2.24
    enska
    2.17
    gué
    2.13
     tung
    2.11
    ྐ
    2.11
    oning
    2.10
    etchup
    2.08
    ходили
    2.08
    POSITIVE LOGITS
    Ь
    2.82
    น์
    2.53
    Ƅ
    2.52
    िलं
    2.42
    ป์
    2.27
    ilize
    2.22
    köz
    2.19
    ƅ
    2.18
     dern
    2.17
    ្សែ
    2.13
    Activations Density 0.115%

    No Known Activations