© 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-65K
    7. 4123
    Prev
    Next
    INDEX
    Explanations

    hyphenated words in URLs

    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_65k_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
     상당히
    0.38
    HARD
    0.36
     тобто
    0.34
    ཊ
    0.34
     ਕਰਨ
    0.34
    ISH
    0.33
    ಥವಾ
    0.33
    ול
    0.33
    ג
    0.33
    ཥ
    0.33
    POSITIVE LOGITS
     soal
    0.45
    ­
    0.42
     khiến
    0.42
     and
    0.41
    :
    0.38
     ও
    0.38
     &
    0.37
    ’
    0.37
     Skyrim
    0.37
     Архивная
    0.37
    Activations Density 0.169%

    No Known Activations