© 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. 70895
    Prev
    Next
    INDEX
    Explanations

    specific types or representations

    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
    ographical
    0.49
    클
    0.49
    PlatformTarget
    0.46
     ordnance
    0.46
     proverbial
    0.45
     astonishment
    0.44
     suppuration
    0.44
    ClrBit
    0.43
     remboursement
    0.43
    깍
    0.43
    POSITIVE LOGITS
    ora
    0.47
    different
    0.45
     sistemi
    0.45
    ्स
    0.44
    fungsi
    0.44
     Sistemi
    0.44
    ຝ
    0.44
     함수
    0.42
    elser
    0.42
     UTIL
    0.42
    Activations Density 0.004%

    No Known Activations