© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 3530
    Prev
    Next
    INDEX
    Explanations

    day or days

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    recer
    0.91
     transition
    0.86
    intend
    0.85
     trayectoria
    0.85
    alth
    0.81
     succession
    0.81
     Еўро
    0.80
    ">—
    0.80
    啾
    0.80
    ∑</
    0.77
    POSITIVE LOGITS
     day
    5.17
    day
    4.84
     DAY
    4.70
    Day
    4.68
     Day
    4.52
    DAY
    4.39
    days
    4.29
     morning
    4.24
     afternoon
    4.15
     days
    4.06
    Activations Density 0.841%

    No Known Activations