© 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. 16-GEMMASCOPE-2-RES-262K
    7. 110121
    Prev
    Next
    INDEX
    Explanations

    endocytosis and internalization

    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_16_width_262k_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
    ^{
    0.61
    IB
    0.55
    И
    0.54
     Fires
    0.52
    ष्ट
    0.52
    Ice
    0.52
    عود
    0.51
    Laser
    0.51
    )
    0.50
    Time
    0.50
    POSITIVE LOGITS
     intensify
    0.63
     abducted
    0.59
     deformed
    0.56
     marcado
    0.56
    𝗋
    0.55
     atteinte
    0.54
    ocytosis
    0.54
     sareng
    0.54
     errado
    0.53
     segmental
    0.53
    Activations Density 0.003%

    No Known Activations