© 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. 83188
    Prev
    Next
    INDEX
    Explanations

    historically referred to

    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
     mahall
    0.50
    зон
    0.46
     svilupp
    0.46
    뚠
    0.46
     තුළ
    0.45
    شرين
    0.45
    isPresent
    0.44
    壓力
    0.44
    સી
    0.43
    શ્વ
    0.43
    POSITIVE LOGITS
     Complimentary
    0.42
     inventing
    0.41
    小数点
    0.40
     ভর্তি
    0.39
     Wikipedia
    0.39
    ikov
    0.39
    Rourke
    0.39
    ቄ
    0.39
    ().
    0.39
    <0x80>
    0.38
    Activations Density 0.004%

    No Known Activations