© 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-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 101605
    Prev
    Next
    INDEX
    Explanations

    ace, awesome, wise

    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
    と
    0.59
    কে
    0.55
    یم
    0.52
    ನ
    0.50
     aventure
    0.49
    ა
    0.49
    но
    0.49
     calendrier
    0.48
    과
    0.48
    თვის
    0.47
    POSITIVE LOGITS
    burning
    0.48
    驳
    0.41
    cking
    0.40
    ier
    0.40
     вед
    0.40
    umen
    0.40
    iping
    0.40
    ckte
    0.39
    uminate
    0.39
    တိုင်း
    0.38
    Activations Density 0.002%

    No Known Activations