© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2989
    Prev
    Next
    INDEX
    Explanations

    DeepMind bash commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    枡
    1.39
     فاذا
    1.20
    뻗
    1.18
    udur
    1.17
     faptul
    1.16
     rusa
    1.14
     vroeg
    1.12
    醸
    1.12
     tarih
    1.12
    usse
    1.11
    POSITIVE LOGITS
    ​
    1.36
     ​
    1.33
    ∼
    1.26
    Compar
    1.19
    ​)
    1.14
     /ˈ
    1.14
    ​​
    1.13
    hapsody
    1.13
     ‍
    1.11
    ¯
    1.10
    Activations Density 0.066%

    No Known Activations