© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 2463
    Prev
    Next
    INDEX
    Explanations

    specific units and measurements

    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
    -
    0.43
    なども
    0.42
    enderung
    0.40
     उसको
    0.39
    җ
    0.38
    <unused444>
    0.38
    I
    0.38
     وغیرہ
    0.37
    сів
    0.37
    мс
    0.37
    POSITIVE LOGITS
     on
    0.55
     is
    0.51
    ب
    0.45
     А
    0.45
     एक
    0.45
    एक
    0.44
     of
    0.43
     một
    0.43
     has
    0.42
     একটি
    0.42
    Activations Density 2.162%

    No Known Activations