© 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. 3367
    Prev
    Next
    INDEX
    Explanations

    programmed to explain refusals

    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
     Willey
    1.39
    вере
    1.29
    Heinz
    1.25
    힘
    1.22
    ativos
    1.20
    Urs
    1.18
    Rita
    1.18
    放射
    1.17
     diversión
    1.17
    elessly
    1.17
    POSITIVE LOGITS
    
    1.23
    
    1.19
    뻥
    1.06
     basing
    1.02
     ​
    1.02
    ](./
    1.00
     Crash
    1.00
    #
    0.96
    ERICAN
    0.93
     Accord
    0.93
    Activations Density 0.044%

    No Known Activations