© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51888
    Prev
    Next
    INDEX
    Explanations

    frequency of events

    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_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
    <0x80>
    0.78
    িল
    0.61
    ן
    0.61
    χρι
    0.59
    s
    0.58
    ре
    0.57
    ail
    0.57
    {
    0.57
    𝙨
    0.57
     in
    0.56
    POSITIVE LOGITS
     frequent
    1.07
    Frequent
    1.04
     frequency
    1.02
     frequ
    1.00
     Frequent
    0.97
     Frequency
    0.89
    频繁
    0.88
    频
    0.87
     czę
    0.83
     fréquence
    0.82
    Activations Density 0.020%

    No Known Activations