© 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. 165055
    Prev
    Next
    INDEX
    Explanations

    locations and interfaces

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

    Secure communication, algorithms, BIOS

    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
     גר
    0.46
     ঋণ
    0.46
    "],[
    0.46
     MIME
    0.46
     ভুলে
    0.45
     ကျွန်
    0.45
     短
    0.45
     把
    0.45
     ପ୍ର
    0.45
     карбо
    0.44
    POSITIVE LOGITS
            
    0.43
     specializes
    0.43
     identifies
    0.40
     hospice
    0.40
    quelle
    0.39
    defense
    0.39
     orice
    0.39
             
    0.38
    protective
    0.38
     serves
    0.38
    Activations Density 0.000%

    No Known Activations