© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9502
    Prev
    Next
    INDEX
    Explanations

    assignment operator is `=`

    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_31_width_16k_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
     を
    0.44
     ohne
    0.43
    floxacin
    0.43
     without
    0.43
     senza
    0.41
     χωρίς
    0.40
     estis
    0.40
     Π
    0.40
    あなたは
    0.40
    insuff
    0.40
    POSITIVE LOGITS
     ఉంటాయి
    0.43
    successor
    0.41
     executions
    0.41
     用于
    0.40
    的应用
    0.40
     moods
    0.39
     inorder
    0.39
     chiều
    0.39
     ounce
    0.39
     stér
    0.38
    Activations Density 0.079%

    No Known Activations