© 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. 13-GEMMASCOPE-2-RES-16K
    7. 10690
    Prev
    Next
    INDEX
    Explanations

    Italian rule, Excel files, Google, Instagram

    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
    Aunque
    1.48
     ocur
    1.47
    㴌
    1.45
    あたり
    1.42
    roscopy
    1.42
    Კ
    1.41
     seized
    1.41
    咛
    1.40
    していますが
    1.39
    edos
    1.39
    POSITIVE LOGITS
     ترین
    1.44
     dizajn
    1.42
    ty
    1.39
    thi
    1.38
     GameObject
    1.36
    린
    1.34
     Nails
    1.34
    ptic
    1.33
    tham
    1.32
     aller
    1.32
    Activations Density 0.000%

    No Known Activations