© 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. 28227
    Prev
    Next
    INDEX
    Explanations

    grey, white, and silver hair

    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
    ot
    0.64
     ശബ്
    0.56
     Jó
    0.53
    tól
    0.53
    烁
    0.53
     hè
    0.52
    <unused67>
    0.50
    夆
    0.50
    ."-
    0.50
    л
    0.50
    POSITIVE LOGITS
    عد
    0.61
     methodologies
    0.55
     attenuation
    0.54
    其他的
    0.53
     indentation
    0.52
     scaffolds
    0.52
     lagoons
    0.52
     tubules
    0.51
     teaspoons
    0.51
     equivalents
    0.50
    Activations Density 0.003%

    No Known Activations