© 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. 40-GEMMASCOPE-2-RES-262K
    7. 21704
    Prev
    Next
    INDEX
    Explanations

    normalizing image pixel values

    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_40_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
     مجلس
    0.47
     नेक
    0.47
    īng
    0.40
     Spani
    0.37
    ەن
    0.37
     doméstica
    0.37
     społ
    0.36
    ="..."
    0.36
     määr
    0.36
     تعیین
    0.36
    POSITIVE LOGITS
     normalization
    1.49
     normalize
    1.47
     normalized
    1.46
    normalize
    1.38
     Normalize
    1.37
    Normalize
    1.33
     normalizing
    1.31
     normalised
    1.30
    Normalization
    1.28
     Normalized
    1.24
    Activations Density 0.024%

    No Known Activations