© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5627
    Prev
    Next
    INDEX
    Explanations

    time durations and quantities

    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
     Toast
    0.90
     every
    0.86
     toe
    0.82
     bread
    0.82
     doors
    0.81
     washes
    0.79
     flushing
    0.79
    澡
    0.77
     metros
    0.76
     toasts
    0.76
    POSITIVE LOGITS
     해석
    1.39
     சுரே
    1.39
    Agreement
    1.33
    刓
    1.32
    বলের
    1.32
     확인함
    1.31
     नाइन
    1.31
     கெல்வின்
    1.31
     الحاس
    1.31
     فونب
    1.30
    Activations Density 0.141%

    No Known Activations