© 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. 2337
    Prev
    Next
    INDEX
    Explanations

    roleplay, link, crash, smile, adult

    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
    堈
    1.49
     rezultat
    1.37
     principi
    1.35
     Puoi
    1.31
    利益
    1.30
     hipótesis
    1.29
     gewährle
    1.29
     formularios
    1.28
     možnosti
    1.26
    бір
    1.26
    POSITIVE LOGITS
    ت
    1.76
    ize
    1.58
    ing
    1.46
     extensively
    1.45
    ously
    1.41
    ized
    1.40
    isieren
    1.37
    ically
    1.32
    izes
    1.29
    ishly
    1.28
    Activations Density 0.624%

    No Known Activations