© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8966
    Prev
    Next
    INDEX
    Explanations

    cooking oil, sounds, numbers, pots

    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
     감
    0.46
     temperament
    0.45
     তাহারই
    0.43
     nije
    0.42
    질
    0.41
     abhid
    0.41
    elah
    0.41
    advantage
    0.41
     تم
    0.41
     sofre
    0.40
    POSITIVE LOGITS
    <0xBF>
    0.49
    ριά
    0.47
    ο
    0.46
    зь
    0.46
    +\
    0.44
    炒
    0.44
    леты
    0.43
    ключа
    0.42
    豪華
    0.42
    раль
    0.42
    Activations Density 0.005%

    No Known Activations