© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5650
    Prev
    Next
    INDEX
    Explanations

    mention any

    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
    ↦
    1.36
    Wikipedia
    1.36
     次元
    1.35
     Ultimate
    1.33
    ⋙
    1.33
    Ultimate
    1.30
    ✱
    1.30
    ╬
    1.30
     interchangeably
    1.29
    National
    1.29
    POSITIVE LOGITS
     receivables
    1.40
     inflow
    1.34
     inflows
    1.32
     bookings
    1.32
    قبال
    1.31
     backlog
    1.29
    损失
    1.28
     recoveries
    1.24
     turnover
    1.24
     cancellations
    1.23
    Activations Density 0.153%

    No Known Activations