© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 49611
    Prev
    Next
    INDEX
    Explanations

    history, specific details, organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    美国
    0.42
    民主
    0.41
     Jefferson
    0.40
    🦃
    0.39
    ากาศ
    0.37
    จัย
    0.37
     Bruce
    0.36
    ᆢ
    0.36
    ㄏ
    0.36
     Incredible
    0.35
    POSITIVE LOGITS
    TAG
    0.41
     precisam
    0.41
     Notiflix
    0.41
     raies
    0.41
    specific
    0.40
     louder
    0.40
     kullanıl
    0.40
     fuc
    0.40
     miso
    0.40
     kaise
    0.39
    Activations Density 0.001%

    No Known Activations