© 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. 2652
    Prev
    Next
    INDEX
    Explanations

    Cross-entropy and receiver operating characteristics

    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
    ine
    0.88
     Amt
    0.77
     void
    0.75
    理
    0.72
     Shown
    0.72
    ha
    0.71
    head
    0.71
     Out
    0.71
     emptied
    0.70
     overpowering
    0.70
    POSITIVE LOGITS
    agamo
    1.58
    urope
    1.57
     femora
    1.47
    横浜
    1.46
     ||=
    1.41
    าม
    1.37
    utsu
    1.35
     datac
    1.34
    ayashi
    1.30
     barcelona
    1.29
    Activations Density 0.153%

    No Known Activations