© 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. 4486
    Prev
    Next
    INDEX
    Explanations

    specify type, use, process, try

    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
    
    1.18
    
    1.13
     EXAMINATION
    1.13
     STUDY
    1.12
     ACO
    1.10
    ","
    1.08
     revue
    1.08
     perin
    1.03
     STUDIES
    1.03
     OSA
    1.01
    POSITIVE LOGITS
    rels
    1.42
     تامین
    1.39
    реа
    1.36
    义
    1.35
    สนับสนุน
    1.34
    aved
    1.32
    ould
    1.32
    ible
    1.30
    ried
    1.27
    iddel
    1.26
    Activations Density 0.011%

    No Known Activations