© 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. 57179
    Prev
    Next
    INDEX
    Explanations

    conservation, track, compared, expansion

    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
    ↵
    0.55
     for
    0.50
     credit
    0.44
     (
    0.43
     over
    0.42
            
    0.42
     For
    0.42
     Nile
    0.42
     Dj
    0.41
    credit
    0.41
    POSITIVE LOGITS
    ໊
    0.52
    संस्करण
    0.51
    >)`](
    0.49
    ಕ್‌
    0.49
    katore
    0.49
    裒
    0.47
    ９
    0.47
    倣
    0.46
     изменение
    0.46
    सायनिक
    0.46
    Activations Density 0.000%

    No Known Activations