© 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-262K
    7. 77278
    Prev
    Next
    INDEX
    Explanations

    appropriateness, bank statement, glaciers, tennis ball

    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
    nymi
    0.56
    անակ
    0.48
    朋友圈
    0.48
     sami
    0.47
     knn
    0.45
     ponsel
    0.44
     ഇക്കാര
    0.44
    <0x99>
    0.44
     secondNumber
    0.43
     линию
    0.43
    POSITIVE LOGITS
     Crater
    0.50
    O
    0.49
    osis
    0.44
     upregulated
    0.44
    OE
    0.44
    الح
    0.44
    .'
    0.43
     Ouais
    0.43
    ма
    0.42
     Worcestershire
    0.42
    Activations Density 0.001%

    No Known Activations