© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17220
    Prev
    Next
    INDEX
    Explanations

    when acquiring or what size

    np_acts-logits-general · gemini-2.5-flash-lite

    refuse to provide dangerous information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_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
    йної
    0.37
     proviso
    0.36
    =>{
    0.36
    Montserrat
    0.36
    տր
    0.36
    zął
    0.36
    ättning
    0.36
     Ψ
    0.35
    Mobs
    0.35
    க்கர
    0.35
    POSITIVE LOGITS
     increment
    0.43
     sia
    0.38
    粥
    0.38
     DSL
    0.37
    increment
    0.37
     Gm
    0.37
    াতে
    0.37
     тай
    0.36
     DEFAULT
    0.36
     brazo
    0.35
    Activations Density 0.013%

    No Known Activations