© 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. 62464
    Prev
    Next
    INDEX
    Explanations

    multilingual confirmations

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

    convergence, confluence, conviction, availability, resistance, combination, agenda, forever

    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
    ùa
    0.46
    த
    0.45
     up
    0.45
     будет
    0.44
     interruption
    0.44
    Aut
    0.44
    AUT
    0.42
    対
    0.42
         
    0.42
    จะไม่
    0.41
    POSITIVE LOGITS
     conferma
    0.51
     vemos
    0.50
     ediyoruz
    0.50
    تماد
    0.48
     continuamos
    0.47
     microbiome
    0.47
     nosso
    0.46
     máme
    0.45
    كلمنا
    0.45
    ثمان
    0.45
    Activations Density 0.000%

    No Known Activations