© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4176
    Prev
    Next
    INDEX
    Explanations

    level badges

    np_acts-logits-general · gemini-2.5-flash-lite

    modulo and remainders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    र्सन
    0.54
    बारक
    0.50
    ोला
    0.50
     Wasch
    0.48
    ອກ
    0.47
    र्मेंद्र
    0.47
    rocery
    0.47
    <unused81>
    0.47
    ल्शियम
    0.47
    <unused33>
    0.46
    POSITIVE LOGITS
     \
    0.54
     
    0.51
     \\
    0.50
    \\\
    0.47
    險
    0.46
     \\\
    0.45
    <eos>
    0.45
    \\
    0.44
     Odd
    0.44
     odd
    0.43
    Activations Density 0.008%

    No Known Activations