© 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. 5429
    Prev
    Next
    INDEX
    Explanations

    refusing requests

    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
     recieve
    1.56
     habitation
    1.51
     Tah
    1.50
    ovirus
    1.50
     recibir
    1.46
    ecoin
    1.45
     перспекти
    1.43
    赴
    1.42
     покри
    1.42
    unker
    1.39
    POSITIVE LOGITS
     otherwise
    1.33
    otherwise
    1.28
     Otherwise
    1.26
    trimenti
    1.23
     OTHERWISE
    1.21
    正しい
    1.20
    阑
    1.16
     cambiato
    1.15
    Autowired
    1.15
    ilj
    1.14
    Activations Density 0.062%

    No Known Activations