© 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. 9907
    Prev
    Next
    INDEX
    Explanations

    past tense events

    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
    WinCounter
    1.35
    <unused793>
    1.30
    ளவில்
    1.30
    <unused1233>
    1.30
    <unused1226>
    1.29
    <unused946>
    1.28
     وړاندوین
    1.28
     مقدار
    1.27
    <unused1218>
    1.26
     حجم
    1.26
    POSITIVE LOGITS
    ↵↵
    1.14
     or
    1.13
     X
    1.11
    /
    1.10
     aka
    1.08
     im
    1.05
     Ins
    1.04
     vecin
    1.03
     en
    1.02
     It
    1.01
    Activations Density 0.000%

    No Known Activations