© 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. 5217
    Prev
    Next
    INDEX
    Explanations

    GPT models and versions

    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
     Finlandia
    1.24
     Prasad
    1.19
     Farmer
    1.11
    hua
    1.06
    蕃
    1.05
     Frozen
    0.97
     Fruit
    0.97
     fru
    0.96
    hika
    0.95
    akot
    0.95
    POSITIVE LOGITS
    퀴
    1.31
     Spitzer
    1.31
     oscillatory
    1.28
    automatically
    1.23
    orbent
    1.23
    LOY
    1.22
     multitud
    1.22
    Jacobi
    1.19
    Correspondence
    1.19
    Enumerable
    1.19
    Activations Density 0.102%

    No Known Activations