© 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. 2024
    Prev
    Next
    INDEX
    Explanations

    sponge or string theory

    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
    <unused674>
    0.61
    <unused1894>
    0.60
    दर्शिता
    0.59
    alous
    0.57
     counterfe
    0.57
    <unused1820>
    0.57
     တို့
    0.55
    <unused1134>
    0.55
     അവൻ
    0.55
    <unused229>
    0.55
    POSITIVE LOGITS
    ל
    0.89
    {
    0.85
    ي
    0.85
    -
    0.77
    ור
    0.76
    >
    0.76
    ↵↵
    0.74
    י
    0.73
    A
    0.72
    м
    0.71
    Activations Density 0.002%

    No Known Activations