© 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. 4662
    Prev
    Next
    INDEX
    Explanations

    timing and duration

    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
     Manc
    0.91
     plain
    0.91
     mall
    0.90
    歪
    0.90
     Viral
    0.90
     Atlas
    0.89
     neben
    0.88
     مخاط
    0.88
     흰
    0.88
     Mika
    0.87
    POSITIVE LOGITS
    September
    1.71
    November
    1.66
    December
    1.64
     earliest
    1.64
    October
    1.62
    February
    1.55
    April
    1.53
    最早
    1.51
    January
    1.50
     dopiero
    1.48
    Activations Density 1.181%

    No Known Activations