© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14245
    Prev
    Next
    INDEX
    Explanations

    time to

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

    character index, role of, water content

    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_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
    Нет
    0.51
    팠
    0.51
    ྰ
    0.50
     rú
    0.49
     fotografías
    0.49
     támogat
    0.49
     capacité
    0.48
    ྜ
    0.48
    Фу
    0.48
     nėra
    0.48
    POSITIVE LOGITS
    nn
    0.54
    nas
    0.53
     Office
    0.52
     necessarily
    0.51
     States
    0.50
    |)
    0.49
    ers
    0.48
    n
    0.48
                    
    0.48
             
    0.47
    Activations Density 0.002%

    No Known Activations