© 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. 62993
    Prev
    Next
    INDEX
    Explanations

    ( not / a lazy / a custom

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

    safety glasses

    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
    穸
    0.47
     தேவை
    0.46
    াপ
    0.46
     atmósfera
    0.45
     experiencias
    0.44
     испыты
    0.44
     varied
    0.43
     Faculties
    0.43
     разнообраз
    0.43
     পাঠ
    0.42
    POSITIVE LOGITS
    📺
    0.50
    inkl
    0.48
                    
    0.47
    itekten
    0.47
       
    0.46
    marshal
    0.46
    replay
    0.45
    n
    0.45
    blkid
    0.45
     ใช่
    0.45
    Activations Density 0.000%

    No Known Activations