© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13522
    Prev
    Next
    INDEX
    Explanations

    expressing possibility or estimation

    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
    𝚞
    2.91
    𝚏
    2.77
    𝚖
    2.76
    st
    2.44
    𝚘
    2.41
    son
    2.31
    𝚊
    2.30
    た
    2.29
    hesia
    2.28
    sa
    2.27
    POSITIVE LOGITS
    msgSender
    2.85
    eritud
    2.80
    arze
    2.79
    ු
    2.77
    ر
    2.75
    יים
    2.72
    י
    2.70
    anesulfonyl
    2.70
    URIComponent
    2.68
    konom
    2.68
    Activations Density 0.014%

    No Known Activations