© 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. 108925
    Prev
    Next
    INDEX
    Explanations

    section introductions or headings

    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
    י
    0.48
    Cr
    0.47
    Perman
    0.46
    CR
    0.45
    Empire
    0.45
     جال
    0.45
    Af
    0.43
    O
    0.43
    ÖR
    0.42
    യ
    0.42
    POSITIVE LOGITS
     txtbtn
    0.44
    gca
    0.44
     ಘೋಷ
    0.43
    퇸
    0.43
     includ
    0.42
     Giving
    0.42
     contato
    0.42
    gd
    0.41
    ươi
    0.41
    adden
    0.41
    Activations Density 0.003%

    No Known Activations