© 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-65K
    7. 46884
    Prev
    Next
    INDEX
    Explanations

    defining specific topics

    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_65k_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
    在
    0.57
    timeout
    0.50
     in
    0.50
    Timeout
    0.46
    皆様
    0.46
    મ
    0.46
    ใน
    0.46
    در
    0.45
    P
    0.45
    OK
    0.44
    POSITIVE LOGITS
    იზ
    0.49
     😏
    0.46
     enshr
    0.46
    rVert
    0.46
    .'"
    0.45
    省级
    0.45
     enshrined
    0.45
    ーーーー
    0.45
     stu
    0.45
     ornate
    0.44
    Activations Density 0.013%

    No Known Activations