© 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. 52688
    Prev
    Next
    INDEX
    Explanations

    iPad Air

    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
    s
    0.65
    es
    0.55
    1
    0.45
    ی
    0.45
    re
    0.43
    as
    0.43
    EN
    0.42
    ких
    0.42
    ς
    0.42
     calculator
    0.42
    POSITIVE LOGITS
    倨
    0.50
    னும்
    0.49
     Turns
    0.48
     där
    0.47
     lavoro
    0.46
    ynku
    0.46
     работу
    0.46
    ेश्वरी
    0.46
     때
    0.45
     Turtles
    0.45
    Activations Density 0.003%

    No Known Activations