© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 88338
    Prev
    Next
    INDEX
    Explanations

    choking hazard

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

    processes with safety warnings

    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_31_width_262k_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
    埓
    0.46
    䢎
    0.44
    
    0.44
    Debbie
    0.43
     любом
    0.42
    QueryParams
    0.42
    Pam
    0.42
    㓈
    0.42
     پاسخ
    0.41
     рекоменду
    0.41
    POSITIVE LOGITS
     combustion
    0.43
     disassembly
    0.42
     scrapping
    0.42
    Editing
    0.41
     editing
    0.41
     swallowing
    0.40
    xml
    0.39
    ophagy
    0.39
    cok
    0.39
    list
    0.38
    Activations Density 0.012%

    No Known Activations