© 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. 4824
    Prev
    Next
    INDEX
    Explanations

    evaluating model performance

    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
    jell
    1.26
    潴
    1.06
    ewords
    1.06
    朦
    1.04
     glycoproteins
    1.02
    leit
    0.98
     diast
    0.94
     coordenadas
    0.93
    ionych
    0.92
    睑
    0.91
    POSITIVE LOGITS
    bench
    2.47
     Execution
    2.21
     benchmarking
    2.15
     Bench
    2.10
     performance
    2.07
     Performance
    2.07
     성능
    2.05
    runtime
    2.04
     execution
    2.02
     Showcase
    2.00
    Activations Density 0.043%

    No Known Activations