© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9556
    Prev
    Next
    INDEX
    Explanations

    technical and biological contexts

    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
     சுண்ணா
    1.53
     savory
    1.52
     ANOTHER
    1.50
     savoury
    1.48
    წვ
    1.46
    آور
    1.45
    LOADING
    1.43
    Է
    1.42
     Addition
    1.42
    stituting
    1.41
    POSITIVE LOGITS
     расходы
    1.82
    iko
    1.50
    ifah
    1.45
     datos
    1.44
     presupuesto
    1.43
     رد
    1.41
    にかく
    1.38
     hozz
    1.38
     też
    1.37
     أو
    1.36
    Activations Density 0.000%

    No Known Activations